Caveat verdict

vulnerability-scanner

12-cool-skills-openclaw-agent

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

A security testing skill explicitly scoped to user-owned websites with clear authorization warnings; the port scanner and SQL injection tester are standard pentesting tools used on targets the user controls, matching the stated purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

28
security
90
transparency
70
maintenance

Findings (6)

Pattern match high

Dynamic import() — loads module at runtime

MASS OPENCLAW SKILL/unzip/api-test-generator/references/api_patterns.md · code · import ( "

Pattern match high

Pipe to python — executes piped content as Python code

MASS OPENCLAW SKILL/unzip/code-converter/references/conversion-patterns.md · prose · downgraded · | Python

Pattern match medium

References sudo — requests elevated privileges

MASS OPENCLAW SKILL/unzip/sandbox-script-executor/references/execution_guide.md · prose · downgraded · sudo

Pattern match medium

pip3 install — installs Python packages at runtime

MASS OPENCLAW SKILL/unzip/sandbox-script-executor/references/execution_guide.md · code · pip3 install

Pattern match medium

apt-get install — installs system packages

MASS OPENCLAW SKILL/unzip/sandbox-script-executor/references/execution_guide.md · prose · downgraded · apt-get install

Pattern match low

Popular HTTP library — network access

MASS OPENCLAW SKILL/unzip/sandbox-script-executor/SKILL.md · prose · downgraded · axios

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API