Skills/ClawHub/wip-ai-devops-toolbox

wip-ai-devops-toolbox@1.9.72

CAUTION· startup only

Publisher claims: "Complete DevOps toolkit for AI-assisted software development. Release pipeline, license compliance, copyright enforcement, repo visibility guard, identity fi..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher parkertoddbrooks · publishing for 253 daysInstalls 4,934Last detonated 29 min ago

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-20 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Destructive command against a filesystem root or device; Destructive command against a filesystem root or device. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 21 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · Pipeline (hotfix): 1. Bump patch version (no suffix) 2. npm publish with --tag latest 3. GitHub release (no deploy-public)
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/codex/SKILL.md:19 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Destructive command against a filesystem root or deviceai/repos/gstack-private/careful/bin/check-careful.sh:96 · Destructive command against a filesystem root or device# docker rm -f / docker system pruneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or deviceai/repos/gstack-private/careful/bin/check-careful.sh:54 · Destructive command against a filesystem root or device# rm -rf / rm -r / rm --recursiveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/SKILL.md:49 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/browse/SKILL.md:18 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/careful/SKILL.md:22 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Pipe-to-shell patternai/repos/gstack-private/SKILL.md:213 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/design-review/SKILL.md:23 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagai/repos/gstack-private/codex/SKILL.md:202 · Fake instruction boundary tag1. `/codex review` or `/codex review <instructions>` — **Review mode** (Step 2A)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedSKILL.md:662 · Destructive file system command detectedwip-readme-format /path/to/repo --check # validate existing README against standardFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/qa/SKILL.md:24 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagai/repos/gstack-private/codex/SKILL.md:429 · Fake instruction boundary tagcodex exec resume <session-id> "<prompt>" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json 2>"$TMPERR" | python3 -c "Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/office-hours/SKILL.md:24 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/unfreeze/SKILL.md:14 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Destructive file system command detectedSKILL.md:660 · Destructive file system command detectedwip-readme-format /path/to/repo --deploy # assemble sections into README.mdFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/freeze/SKILL.md:28 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Destructive file system command detectedSKILL.md:661 · Destructive file system command detectedwip-readme-format /path/to/repo --dry-run # preview without writingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedai/repos/gstack-private/careful/SKILL.md:39 · Destructive file system command detected| `rm -rf` / `rm -r` / `rm --recursive` | `rm -rf /var/data` | Recursive delete |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/ship/SKILL.md:18 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/plan-eng-review/SKILL.md:20 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Destructive file system command detectedSKILL.md:659 · Destructive file system command detectedwip-readme-format /path/to/repo # generate README-init-*.md section filesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/setup-browser-cookies/SKILL.md:15 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagai/repos/gstack-private/codex/SKILL.md:396 · Fake instruction boundary tagcodex exec "<prompt>" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json 2>"$TMPERR" | python3 -c "Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patternai/repos/gstack-private/scripts/gen-skill-docs.ts:260 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If \`bun\` is not installed: \`curl -fsSL https://bun.sh/install | bash\``;Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/qa-only/SKILL.md:17 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/review/SKILL.md:19 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/gstack-upgrade/SKILL.md:15 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/plan-ceo-review/SKILL.md:21 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/document-release/SKILL.md:20 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagai/repos/gstack-private/codex/SKILL.md:311 · Fake instruction boundary tagcodex exec "<prompt>" -s read-only -c 'model_reasoning_effort="xhigh"' --enable web_search_cached --json 2>/dev/null | python3 -c "Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/plan-design-review/SKILL.md:21 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/design-consultation/SKILL.md:23 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/investigate/SKILL.md:33 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/guard/SKILL.md:33 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/retro/SKILL.md:18 · HTML comment carrying imperative instructions to the agentRegenerate: bun run gen:skill-docsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Pipe-to-shell patternai/repos/gstack-private/browse/SKILL.md:178 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Auto-update or dynamic fetch configurationai/repos/gstack-private/document-release/SKILL.md:277 · Auto-update or dynamic fetch configuration — agent may load new code at runtime- **Auto-update** — Factual corrections clearly warranted by the diff: adding an item to aFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Refusal suppressionai/repos/gstack-private/qa/SKILL.md:699 · Refusal suppression — attempting to prevent safety responses…ee. This is critical — without it, screenshots are invisible to the user. 12. **Never refuse to use the browser.** When the user invokes /qa or /qa-only, they are requestin…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Refusal suppressionai/repos/gstack-private/qa-only/SKILL.md:493 · Refusal suppression — attempting to prevent safety responses…ee. This is critical — without it, screenshots are invisible to the user. 12. **Never refuse to use the browser.** When the user invokes /qa or /qa-only, they are requestin…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Credential pass-through configurationai/repos/gstack-private/codex/SKILL.md:260 · Credential pass-through configuration — agent relays sensitive credentialsGATE: PASS Tokens: 14,331 | Est. cost: ~$0.12Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Pipe-to-shell patternai/repos/gstack-private/qa-only/SKILL.md:192 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Pipe-to-shell patternai/repos/gstack-private/qa/SKILL.md:242 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedai/repos/gstack-private/document-release/SKILL.md:470 · Destructive file system command detectedrm -f /tmp/gstack-pr-body-$$.mdFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/qa/SKILL.md:373 · Instructs the agent to modify its persistent memory or instruction files### B7. Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Refusal suppressionai/repos/gstack-private/design-consultation/SKILL.md:367 · Refusal suppression — attempting to prevent safety responses- Always accept the user's final choice. Never refuse to proceed.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/design-consultation/SKILL.md:502 · Instructs the agent to modify its persistent memory or instruction files- A) Ship it — write DESIGN.md and CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patternai/repos/gstack-private/design-consultation/SKILL.md:219 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/design-review/SKILL.md:352 · Instructs the agent to modify its persistent memory or instruction files### B7. Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patternai/repos/gstack-private/design-review/SKILL.md:221 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedai/repos/gstack-private/careful/bin/check-careful.sh:96 · Destructive file system command detected# docker rm -f / docker system pruneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedai/repos/gstack-private/careful/bin/check-careful.sh:54 · Destructive file system command detected# rm -rf / rm -r / rm --recursiveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/design-consultation/SKILL.md:489 · Instructs the agent to modify its persistent memory or instruction files**Update CLAUDE.md** (or create it if it doesn't exist) — append this section:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Hex-encoded URLai/repos/gstack-private/browse/test/url-validation.test.ts:50 · Hex-encoded URL — attempt to bypass URL filteringexpect(() => validateNavigationUrl('http://0xA9FEA9FE/')).toThrow(/cloud metadata/i);Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/path-validation.test.ts:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => validateOutputPath('/tmp/../etc/passwd')).toThrow(/Path must be within/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/SKILL.md:20 · Instructs the agent to modify its persistent memory or instruction files…e/MEMORY.md`, `workspace/IDENTITY.md`, `workspace/SOUL.md`, `workspace/WHERE-TO-WRITE.md`, `workspace/HEARTBEAT.md`, `workspace/memory/*.md`, `CLAUDE.md`. Worktree convention: `.worktrees/<repo>--<branch>/`. Bootstrap compound (`gi…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellai/repos/gstack-private/browse/SKILL.md:178 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actionai/repos/gstack-private/design-review/SKILL.md:408 · File type combined with upload action — agent may exfiltrate local data filesRun full audit, then load previous `design-baseline.json`. Compare: per-category grade deltas, new findings, resolved findings. Output regression table in report.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellai/repos/gstack-private/qa/SKILL.md:242 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Destructive file system command detectedtools/wip-branch-guard/test.sh:141 · Destructive file system command detectedtest_case "rm on main-tree path still denies" deny Bash "rm /some/repo/file.md" trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandai/repos/gstack-private/browse/test/commands.test.ts:33 · Process kill command — agent can terminate processes// Force kill browser instead of graceful close (avoids hang)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/gen-skill-docs.ts:1233 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`FRESH: ${relOutput}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandai/repos/gstack-private/plan-ceo-review/SKILL.md:229 · Process kill command — agent can terminate processes11. **Wartime awareness** — Correctly diagnose peacetime vs wartime. Peacetime habits kill wartime companies (Horowitz).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedtools/wip-readme-format/SKILL.md:38 · Destructive file system command detectedwip-readme-format /path/to/repo # rewrite README.mdFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/gen-skill-docs.ts:1237 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`GENERATED: ${relOutput}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/commands.test.ts:1755 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait handleWriteCommand('cookie-import', ['../../etc/shadow'], bm);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/commands.test.ts:1716 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait handleReadCommand('eval', ['../../etc/passwd'], bm);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/dev-skill.ts:41 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` [check] \u274c ${output} (${totalValid} valid)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellai/repos/gstack-private/scripts/gen-skill-docs.ts:260 · Remote installer piped to shell3. If \`bun\` is not installed: \`curl -fsSL https://bun.sh/install | bash\``;Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/commands.test.ts:1764 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait handleWriteCommand('cookie-import', ['/etc/passwd'], bm);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellai/repos/gstack-private/design-consultation/SKILL.md:219 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Destructive file system command detectedtools/wip-readme-format/format.mjs:5 · Destructive file system command detected// wip-readme-format /path/to/repo # generate README-init-*.md section filesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedtools/wip-readme-format/format.mjs:6 · Destructive file system command detected// wip-readme-format /path/to/repo --deploy # assemble sections into README.md + TECHNICAL.mdFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedtools/wip-readme-format/format.mjs:7 · Destructive file system command detected// wip-readme-format /path/to/repo --dry-run # preview without writingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Pipe-to-shell patternai/repos/gstack-private/setup-browser-cookies/SKILL.md:185 · Pipe-to-shell pattern — downloads and immediately executes remote code3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedtools/wip-branch-guard/test.sh:118 · Destructive file system command detectedtest_case "rm in /tmp" allow Bash "rm /tmp/test.txt"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/commands.test.ts:1725 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait handleReadCommand('eval', ['/etc/passwd'], bm);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellai/repos/gstack-private/SKILL.md:213 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellai/repos/gstack-private/qa-only/SKILL.md:192 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandai/repos/gstack-private/browse/src/cli.ts:91 · Process kill command — agent can terminate processes// Force kill if still aliveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/path-validation.test.ts:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => validateReadPath('/etc/passwd')).toThrow(/Absolute path must be within/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/gen-skill-docs.ts:621 · File type combined with upload action — agent may exfiltrate local data filesRun full audit, then load previous \`design-baseline.json\`. Compare: per-category grade deltas, new findings, resolved findings. Output regression table in report.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/path-validation.test.ts:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => validateReadPath('src/../../etc/passwd')).toThrow(/Path traversal/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL to the cloud instance metadata addressai/repos/gstack-private/browse/test/url-validation.test.ts:38 · URL to the cloud instance metadata address — reads the VM's credentialsexpect(() => validateNavigationUrl('http://169.254.169.254/latest/meta-data/')).toThrow(/cloud metadata/i);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Remote installer piped to shellai/repos/gstack-private/design-review/SKILL.md:221 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Auto-update or dynamic fetch configurationtools/wip-release/core.mjs:875 · Auto-update or dynamic fetch configuration — agent may load new code at runtime* Auto-update version/date lines in product docs before the release commit.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionSKILL.md:506 · File type combined with upload action — agent may exfiltrate local data files- `.license-guard.json` with WIP Computer defaultsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Auto-update or dynamic fetch configurationtools/wip-release/core.mjs:2214 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// 3.75. Auto-update product docs version/dateFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/gen-skill-docs.ts:1230 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`STALE: ${relOutput}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detectedtools/wip-readme-format/format.mjs:21 · Destructive file system command detected// 1. wip-readme-format /path/to/repo ... generates section filesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/path-validation.test.ts:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => validateReadPath('../../../etc/passwd')).toThrow(/Path traversal/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/browse/test/url-validation.test.ts:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => validateNavigationUrl('file:///etc/passwd')).toThrow(/scheme.*not allowed/i);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/ship/SKILL.md:422 · Instructs the agent to modify its persistent memory or instruction files### B7. Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedtools/wip-readme-format/SKILL.md:40 · Destructive file system command detectedwip-readme-format /path/to/repo --check # validate, exit 0/1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedtools/wip-readme-format/format.mjs:8 · Destructive file system command detected// wip-readme-format /path/to/repo --check # validate existing README, exit 0/1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedtools/wip-readme-format/SKILL.md:39 · Destructive file system command detectedwip-readme-format /path/to/repo --dry-run # preview without writingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/dev-skill.ts:49 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` [check] \u2705 ${output} — ${totalValid} commands, all valid`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellai/repos/gstack-private/setup-browser-cookies/SKILL.md:185 · Remote installer piped to shell3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Destructive file system command detectedai/repos/gstack-private/test/hook-scripts.test.ts:74 · Destructive file system command detectedtest('rm -rf /var/data warns with recursive delete message', () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontools/wip-license-hook/src/cli/index.ts:113 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatGateOutput(safe, alerts));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Destructive file system command detectedai/repos/gstack-private/test/hook-scripts.test.ts:73 · Destructive file system command detecteddescribe('rm -rf / rm -r', () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/test/skill-e2e.test.ts:2076 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileWrite DESIGN.md and CLAUDE.md (or update it) in the working directory.`,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detectedai/repos/gstack-private/test/hook-scripts.test.ts:258 · Destructive file system command detectedconst rawJson = '{"tool_input":{"command":\n"rm -rf /tmp/important"}}';Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagetools/wip-license-hook/hooks/pre-pull.sh:18 · npx invocation of non-well-known package — may execute untrusted codeHOOK_CMD="npx @wipcomputer/wip-license-hook"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiontools/wip-universal-installer/install.js:921 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' Tip: LDM OS could not be installed automatically. Try: npm install -g @wipcomputer/wip-ldm-os');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontools/wip-repo-permissions-hook/cli.js:35 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' wip-repo-permissions check wipcomputer/wip-bridge');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-19--cc-opus--implement-claude-md.md:224 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file1. **Toolbox repo** — dogfood first, manually write CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-19--cc-opus--implement-claude-md.md:259 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file| `tools/wip-repos/check.mjs` | **Modify** — add CLAUDE.md validation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-13--cc-mini--rename-to-wip-code.md:356 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file… `guide/DEV-GUIDE.md` path that doesn't exist. Fix this in Step 6 as part of the CLAUDE.md update. This is a pre-existing bug (references `wip-dev-tools-private` which was rena…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-19--cc-opus--implement-claude-md.md:205 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- `wip-file-guard` blocks Write on CLAUDE.md, blocks Edit removing >2 net linesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
HTML comment carrying imperative instructions to the agentai/repos/gstack-private/browse/test/fixtures/qa-eval-spa.html:22 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileBUG 1: broken route — typo "prodcts" instead of "products"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/test/skill-llm-eval.test.ts:610 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filejudgeGoal: 'how to audit and update project documentation after code ships: README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md, CHANGELOG, TODOS',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
File permission modification commandtools/wip-license-hook/hooks/pre-pull.sh:5 · File permission modification command — agent changes file ownership/permissions# Install: cp hooks/pre-pull.sh .git/hooks/pre-merge-commit && chmod +x .git/hooks/pre-merge-commitFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/skill-check.ts:85 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` \u274c ${output.padEnd(30)} — generated file missing! Run: bun run gen:skill-docs`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/README.md:16 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- Onboarding-before-first-write: requires Read of `README.md`, `CLAUDE.md`, and any `*RUNBOOK*.md` / `*LANDMINES*.md` / `WORKFLOW*.md` at repo root before the first write.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-13--cc-mini--rename-to-wip-code.md:228 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file1. Update `~/.openclaw/CLAUDE.md` (all three path references)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/skill-check.ts:80 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` \u26a0\ufe0f ${output.padEnd(30)} — no template`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionai/repos/gstack-private/test/skill-e2e.test.ts:2836 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Output has coverage summary: ${hasCoverage}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagetools/wip-license-hook/hooks/pre-push.sh:18 · npx invocation of non-well-known package — may execute untrusted codeHOOK_CMD="npx @wipcomputer/wip-license-hook"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiontools/wip-universal-installer/install.js:718 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' --json Output detection results as JSON');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontools/wip-release/core.mjs:2138 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` [dry run] Would publish to npm (@wipcomputer scope)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionai/repos/gstack-private/scripts/skill-check.ts:88 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` \u2705 ${tmpl.padEnd(30)} \u2192 ${output}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandtools/wip-license-hook/hooks/pre-push.sh:5 · File permission modification command — agent changes file ownership/permissions# Install: cp hooks/pre-push.sh .git/hooks/pre-push && chmod +x .git/hooks/pre-pushFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction files_trash/RELEASE-NOTES-v1-9-51.md:5 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdded TOOLS.md, MEMORY.md, IDENTITY.md, SOUL.md, WHERE-TO-WRITE.md, HEARTBEAT.md to the shared state allowlist. Both agents can now write to workspace files on main without being blocked.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/README.md:55 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…m -rf .claude/skills/gstack/.git && cd .claude/skills/gstack && ./setup`** then add a "gstack" section to this project's CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:856 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdded TOOLS.md, MEMORY.md, IDENTITY.md, SOUL.md, WHERE-TO-WRITE.md, HEARTBEAT.md to the shared state allowlist. Both agents can now write to workspace files on main without being blocked.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/README.md:51 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…ck.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiontools/wip-repo-permissions-hook/cli.js:36 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' wip-repo-permissions audit wipcomputer');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/test/hook-scripts.test.ts:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagetools/wip-license-hook/hooks/pre-pull.sh:17 · npx invocation of non-well-known package — may execute untrusted codeelif command -v npx &>/dev/null; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive command against a filesystem root or deviceai/repos/gstack-private/test/hook-scripts.test.ts:73 · Destructive command against a filesystem root or devicedescribe('rm -rf / rm -r', () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-19--cc-opus--implement-claude-md.md:254 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file| `tools/wip-repo-init/init.mjs` | **Modify** — add CLAUDE.md generation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/dev-updates/2026-03-07--15-50--cc-mini--claude-md-repo-paths-fix.md:1 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file# Dev Update: CLAUDE.md Repo Paths Fix + Boot Sequence EnforcementFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesai/_sort/_trash/ai_old/_trash/dev-updates/2026-03-07--15-50--cc-mini--claude-md-repo-paths-fix.md:1 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file# Dev Update: CLAUDE.md Repo Paths Fix + Boot Sequence EnforcementFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionai/repos/gstack-private/test/skill-e2e.test.ts:2834 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Output has GAP markers: ${hasGap}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Destructive file system command detectedai/repos/gstack-private/test/hook-scripts.test.ts:75 · Destructive file system command detectedconst { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf /var/data'));Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontools/wip-readme-format/format.mjs:270 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' wip-readme-format ... reformat a README to follow the WIP Computer standard');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionai/repos/gstack-private/test/skill-e2e.test.ts:2835 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Output has TESTED markers: ${hasTested}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesai/repos/gstack-private/scripts/gen-skill-docs.ts:1107 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file### B7. Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
URL to a private-network addressai/repos/gstack-private/browse/test/url-validation.test.ts:22 · URL to a private-network address — a LAN or development targetexpect(() => validateNavigationUrl('http://192.168.1.1')).not.toThrow();Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/bugs/2026-03-13--cc-mini--merge-deploy-install-conflated.md:66 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd to CLAUDE.md and the Dev Guide:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiontools/wip-license-hook/dist/cli/index.js:99 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatGateOutput(safe, alerts));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesai/product/plans-prds/upcoming/2026-03-13--cc-mini--rename-to-wip-code.md:229 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file2. Update `~/.claude/CLAUDE.md` (mirror)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathsai/repos/gstack-private/test/hook-scripts.test.ts:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagetools/wip-license-hook/hooks/pre-push.sh:17 · npx invocation of non-well-known package — may execute untrusted codeelif command -v npx &>/dev/null; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/test.sh:57 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file'{"tool_name":"Edit","tool_input":{"file_path":"/foo/CLAUDE.md","old_string":"a\nb\nc\nd\ne\nf","new_string":"replaced"}}' \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/REFERENCE.md:55 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileecho '{"tool_name":"Write","tool_input":{"file_path":"/foo/CLAUDE.md"}}' | node guard.mjsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/test.sh:43 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filecheck "Block Write to CLAUDE.md" \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-repos/claude.mjs:118 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file* Update the ecosystem section in a CLAUDE.md file.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/test.sh:44 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file'{"tool_name":"Write","tool_input":{"file_path":"/foo/CLAUDE.md","content":"new"}}' \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/README.md:83 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filePASS: Block Write to CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/test.sh:56 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filecheck "Block Edit removing 5 lines from CLAUDE.md" \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/README.md:87 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filePASS: Allow Edit adding lines to CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/test.sh:234 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file# Build a tmp repo with README + CLAUDE.md, then add a git worktree. TheFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/README.md:86 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filePASS: Block Edit removing 5 lines from CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-repos/claude.mjs:238 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileconsole.log(` [update] ${repoName}/CLAUDE.md (${relevant.length} related repos)`);Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/test.sh:461 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filegit add README.md CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/test.sh:313 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filelayer3_call "iso-b" "Write" "$LAYER3_REPO/iso-b1.md" "deny" "iso: session B still needs its own CLAUDE.md read"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-file-guard/test.sh:60 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filecheck "Allow Edit adding lines to CLAUDE.md" \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/test.sh:149 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filetest_case "Write auto-memory index" allow Write "$HOME/.claude/projects/-Users-lesa-example/memory/MEMORY.md"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/guard.mjs:658 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// Required reads for first write in a repo. Root-level README.md, CLAUDE.md,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestools/wip-branch-guard/test.sh:245 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filegit add README.md CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈154,214 tok
37 files · 411 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim parkertoddbrooks: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim parkertoddbrooksPropose a patch to the maintainer