openclaw-ultimate-suite@3.0.0
BLOCKED· static onlyPublisher 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.
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 onlyThis 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
# 自动拦截 rm -rf / 等命令Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- 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.ENV_FILE="${ROOT_DIR}/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.dynamic — DynamicFetcher only (full JS, ~10-30s)Fix: Pin versions and sources; vendor anything fetched at install time.ENV_EXAMPLE="${ROOT_DIR}/.env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| Auto-update content | Formulas | Fields | Links |Fix: Pin versions and sources; vendor anything fetched at install time.log "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.export 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.- `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `.env`, secrets, token-like stringsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.… "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.".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# 自动拦截 rm -rf / 等命令Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.{"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.• 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.chmod +x xiaohongshu-mcp-darwin-arm64 xiaohongshu-login-darwin-arm64Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.npx playwright testFix: Pin versions and sources; vendor anything fetched at install time.npx playwright codegen https://example.comFix: Pin versions and sources; vendor anything fetched at install time.export 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.| ⛔ 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."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.• Requests elevated/sudo permissionsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "${pid}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."criteria_text": "Contains destructive commands (rm -rf, dd if=/dev, mkfs, fork bomb like :(){ }, chmod 777, DROP DATABASE, curl|bash, wget+execute)"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.npx playwright test --headedFix: Pin versions and sources; vendor anything fetched at install time.chmod +x "${TARGET_SKILL_DIR}/scripts/browse_page.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.sensitive_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.• 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.if path.name.startswith(".env"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx @playwright/mcp --headlessFix: Pin versions and sources; vendor anything fetched at install time."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.- 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.kill "${PID}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill -0 "${pid}" >/dev/null 2>&1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.raw = 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.chmod +x ~/.openclaw/scripts/ironclaw_audit.pyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod +x "${TARGET_SKILL_DIR}/scripts/search_local_web.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.npx playwright test --trace onFix: Pin versions and sources; vendor anything fetched at install time.chmod +x ~/.openclaw/guardian.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.kill "${pid}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."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.if path.name.startswith(".env"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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%- 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.
- 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.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- 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.