Skills/ClawHub/skillvet

skillvet@2.0.9

CAUTION· install only

Publisher claims: "Security scanner for ClawHub/community skills — detects malware, credential theft, exfiltration, prompt injection, obfuscation, homograph attacks, ANSI injec..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher oakencore · publishing for 270 daysInstalls 4,368Last detonated 5 min ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection attempt; Access to sensitive file paths; Pipe to network utility. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Prompt injection attemptSKILL.md:132 · Prompt injection attempt — 'ignore previous instructions'| 9 | Prompt injection in markdown | "ignore previous instructions" in SKILL.md |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsSKILL.md:167 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| 44 | Credential file access | Direct reads of `.env`, `.pem`, `.aws/credentials` |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 pathstests/run-tests.sh:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Check #8 — .env file theftFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe to network utilityscripts/skill-audit.sh:899 · Pipe to network utility — potential reverse shell…ackdoor pattern: ${content:0:120}" "41" done < <(grep -rnE '(nohup.*(curl|wget|nc |ncat|bash -c|/dev/tcp)|disown.*(curl|wget|bash)|setsid.*(curl|wget|bash|nc))' "…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/skill-audit.sh:798 · File permission modification command — agent changes file ownership/permissions# 34. xattr/chmod on downloaded files (ENCODED)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Pipe-to-shell patternSKILL.md:169 · Pipe-to-shell pattern — downloads and immediately executes remote code| 46 | GitHub raw content execution | `curl raw.githubusercontent.com/... \| bash` |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandtests/run-tests.sh:297 · File permission modification command — agent changes file ownership/permissions# Check #34 — xattr/chmod dropperFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Pipe to network utilityscripts/skill-audit.sh:777 · Pipe to network utility — potential reverse shellgrep -qE '(curl|wget|nc |ncat|fetch\(|requests\.|http\.|socket\.)' "$file" 2>/dev/null && has_network=1Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/skill-audit.sh:422 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdone < <(grep -rnE '(\.\./\.\./|/etc/passwd|/etc/shadow|~\/\.bashrc|~\/\.ssh|~\/\.aws|~\/\.clawdbot|~\/\.config|\/home\/[a-z])' "$SKILL_DIR" $CODE_INCLUDES 2>/dev/null || true)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:138 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| 15 | Shipped .env files | .env files (not .example) in the skill |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/skill-audit.sh:195 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files[8]="Do not read .env files programmatically. Use declared environment variables."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/skill-audit.sh:198 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file[11]="Do not modify agent config files (AGENTS.md, SOUL.md, etc.)."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/run-tests.sh:181 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Check #15 — shipped .env filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/skill-audit.sh:801 · File permission modification command — agent changes file ownership/permissionsverbose "Running check #34: xattr/chmod dropper"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsscripts/skill-audit.sh:295 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files-o -name "*.txt" -o -name "*.env*" -o -name "Dockerfile*" -o -name "Makefile" \Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Pipe-to-shell patternSKILL.md:144 · Pipe-to-shell pattern — downloads and immediately executes remote code| 21 | Pipe-to-shell | `curl \| bash` (HTTP and HTTPS) |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
URL shortener detectedSKILL.md:97 · URL shortener detected — destination cannot be verifiedconst url = "https://bit.ly/legit-link"; // skillvet-ignoreFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandSKILL.md:157 · File permission modification command — agent changes file ownership/permissions| 34 | xattr/chmod dropper | macOS Gatekeeper bypass: download, `xattr -c`, `chmod +x`, execute |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/skill-audit.sh:806 · File permission modification command — agent changes file ownership/permissionsadd_finding "CRITICAL" "$rel_file" "$line" "Download + xattr/chmod -- macOS Gatekeeper bypass (AMOS pattern): ${content:0:120}" "34"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:169 · Remote installer piped to shell| 46 | GitHub raw content execution | `curl raw.githubusercontent.com/... \| bash` |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsSKILL.md:131 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| 8 | .env file theft | dotenv loading in scripts (not docs) |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandSKILL.md:158 · File permission modification command — agent changes file ownership/permissions| 35 | ClickFix download+execute chain | `curl -o /tmp/x && chmod +x && ./x`, `open -a` with downloads |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:144 · Remote installer piped to shell| 21 | Pipe-to-shell | `curl \| bash` (HTTP and HTTPS) |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsSKILL.md:128 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| 5 | Path traversal / sensitive files | `../../`, `~/.ssh`, `~/.clawdbot` |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 filesSKILL.md:134 · Instructs the agent to modify its persistent memory or instruction files| 11 | Agent config tampering | Write/modify AGENTS.md, SOUL.md, clawdbot.json |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/skill-audit.sh:202 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files[15]="Remove .env files from the skill. Use .env.example templates instead."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈2,669 tok
1 file · 6 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

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

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Pipe to network utility≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unclaimed publisher≈ +8 on the totalClaim oakencore: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim oakencorePropose a patch to the maintainer