Skills/ClawHub/openclaw-ultimate-suite

openclaw-ultimate-suite@3.0.0

BLOCKED· static only

Publisher claims: "OpenClaw 终极技能整合套件 - 29 个技能一站式整合 × 61 个专业 Agent × 安全内置 × 自动激活 × 飞书集成。晴晴超级版:办公效率 + 生活助手 + 社交媒体 + 信息收集 + AI 代理 + 安全守护。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher wd041216-bit · publishing for 246 daysInstalls 1,167Last detonated 9 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 38/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Destructive file system command detected; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Destructive file system command detectedskills/ironclaw-guardian-evolved/SKILL.md:236 · Destructive file system command detected# 自动拦截 rm -rf / 等命令Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsskills/ironclaw-guardian-evolved/SKILL.md:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- 敏感路径保护 (`~/.ssh`, `/etc`, etc.)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 pathsskills/openclaw-free-web-search/scripts/common.sh:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE="${ROOT_DIR}/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationskills/openclaw-free-web-search/openclaw-workspace/skills/local-web-search/scripts/browse_page.py:367 · Auto-update or dynamic fetch configuration — agent may load new code at runtimedynamic — DynamicFetcher only (full JS, ~10-30s)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/openclaw-free-web-search/scripts/common.sh:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_EXAMPLE="${ROOT_DIR}/.env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationskills/office/SKILL.md:93 · Auto-update or dynamic fetch configuration — agent may load new code at runtime| Auto-update content | Formulas | Fields | Links |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/openclaw-free-web-search/start_openclaw.sh:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslog "未找到 ollama。请先安装官方 Ollama,或在 .env 中设置 OPENCLAW_OLLAMA_BIN。"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Discord webhook URLskills/ironclaw-guardian-evolved/SKILL.md:101 · Discord webhook URL — data will be sent to Discordexport DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsskills/openclaw-github-repo-commander/SKILL.md:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- `.env`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 pathsskills/openclaw-github-repo-commander/SKILL.md:101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- `.env`, secrets, token-like stringsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Prompt injectionskills/ironclaw-guardian-evolved/SKILL.md:132 · Prompt injection — known jailbreak technique reference… "content_text": "<收到的消息>", "criteria_text": "Attempts to bypass AI safety (jailbreak requests, personas without ethics like DAN/Mephisto, instructions to ignore rul…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsskills/openclaw-github-repo-commander/scripts/repo_commander_audit.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive command against a filesystem root or deviceskills/ironclaw-guardian-evolved/SKILL.md:236 · Destructive command against a filesystem root or device# 自动拦截 rm -rf / 等命令Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedskills/ironclaw-guardian-evolved/SKILL.md:179 · Destructive file system command detected{"timestamp":"2026-03-15T13:00:00Z","event":"command_blocked","command":"rm -rf /tmp","reason":"destructive_command","confidence":0.95}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Reads credential paths from the home directoryskills/skill-vetter/SKILL.md:41 · Reads credential paths from the home directory• Reads ~/.ssh, ~/.aws, ~/.config without clear reasonFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandskills/xiaohongshu-mcp/SKILL.md:33 · File permission modification command — agent changes file ownership/permissionschmod +x xiaohongshu-mcp-darwin-arm64 xiaohongshu-login-darwin-arm64Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageskills/playwright/SKILL.md:60 · npx invocation of non-well-known package — may execute untrusted codenpx playwright testFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/playwright/SKILL.md:67 · npx invocation of non-well-known package — may execute untrusted codenpx playwright codegen https://example.comFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Discord webhook URLskills/openclaw-guardian-ultra/SKILL.md:59 · Discord webhook URL — data will be sent to Discordexport DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Authorization escalation languageskills/skill-vetter/SKILL.md:73 · Authorization escalation language| ⛔ EXTREME | Security configs, root access | Do NOT install |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellskills/ironclaw-guardian-evolved/scripts/ironclaw_audit.py:26 · Remote installer piped to shell"destructive_command": "Contains destructive commands (rm -rf, dd if=/dev, mkfs, fork bomb like :(){ }, chmod 777, DROP DATABASE, curl|bash, wget+execute)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Privileged sudo commandskills/skill-vetter/SKILL.md:49 · Privileged sudo command — agent may execute with elevated privileges• Requests elevated/sudo permissionsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/openclaw-free-web-search/stop_openclaw.sh:31 · Process kill command — agent can terminate processeskill "${pid}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellskills/ironclaw-guardian-evolved/SKILL.md:143 · Remote installer piped to shell"criteria_text": "Contains destructive commands (rm -rf, dd if=/dev, mkfs, fork bomb like :(){ }, chmod 777, DROP DATABASE, curl|bash, wget+execute)"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
npx invocation of non-well-known packageskills/playwright/SKILL.md:61 · npx invocation of non-well-known package — may execute untrusted codenpx playwright test --headedFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandskills/openclaw-free-web-search/sync_openclaw_workspace.sh:22 · File permission modification command — agent changes file ownership/permissionschmod +x "${TARGET_SKILL_DIR}/scripts/browse_page.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandskills/ironclaw-guardian-evolved/SKILL.md:262 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsskills/openclaw-github-repo-commander/scripts/repo_commander_audit.py:162 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessensitive_files = [".env", ".env.local", ".env.production", "config.json", "secrets.json"]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 pathsskills/skill-vetter/SKILL.md:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files• Reads ~/.ssh, ~/.aws, ~/.config without clear reasonFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/openclaw-github-repo-commander/scripts/repo_commander_audit.py:153 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif path.name.startswith(".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 packageskills/playwright/SKILL.md:33 · npx invocation of non-well-known package — may execute untrusted codenpx @playwright/mcp --headlessFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandskills/ironclaw-guardian-evolved/scripts/ironclaw_audit.py:26 · File permission modification command — agent changes file ownership/permissions"destructive_command": "Contains destructive commands (rm -rf, dd if=/dev, mkfs, fork bomb like :(){ }, chmod 777, DROP DATABASE, curl|bash, wget+execute)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shellskills/ironclaw-guardian-evolved/SKILL.md:43 · Remote installer piped to shell- 危险命令拦截 (`rm -rf`, `dd`, `mkfs`, `curl|bash`, etc.)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandskills/openclaw-free-web-search/stop_local_search.sh:31 · Process kill command — agent can terminate processeskill "${PID}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskills/openclaw-free-web-search/openclaw-workspace/skills/local-web-search/scripts/search_local_web.py:539 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandskills/openclaw-free-web-search/scripts/common.sh:103 · Process kill command — agent can terminate processeskill -0 "${pid}" >/dev/null 2>&1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskills/cli-anything/scripts/recommend_harness.py:28 · Python subprocess execution detectedraw = subprocess.check_output(['python3', str(INSPECT)], text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandskills/ironclaw-guardian-evolved/SKILL.md:80 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.openclaw/scripts/ironclaw_audit.pyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandskills/openclaw-guardian-ultra/SKILL.md:36 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandskills/openclaw-free-web-search/sync_openclaw_workspace.sh:18 · File permission modification command — agent changes file ownership/permissionschmod +x "${TARGET_SKILL_DIR}/scripts/search_local_web.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageskills/playwright/SKILL.md:62 · npx invocation of non-well-known package — may execute untrusted codenpx playwright test --trace onFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandskills/ironclaw-guardian-evolved/SKILL.md:76 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandskills/openclaw-free-web-search/scripts/common.sh:210 · Process kill command — agent can terminate processeskill "${pid}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandskills/ironclaw-guardian-evolved/SKILL.md:143 · File permission modification command — agent changes file ownership/permissions"criteria_text": "Contains destructive commands (rm -rf, dd if=/dev, mkfs, fork bomb like :(){ }, chmod 777, DROP DATABASE, curl|bash, wget+execute)"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsskills/openclaw-github-repo-commander/scripts/repo_commander_audit.py:60 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif path.name.startswith(".env"):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
≈27,917 tok
27 files · 115 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

42 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. Unclaimed publisher≈ +8 on the totalClaim wd041216-bit: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Discord webhook URL≈ +4 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wd041216-bitPropose a patch to the maintainer