ClawAudit verdict
Mapping-Skill
mapping-skill
The skill searches and extracts AI/ML talent information with clear documentation and usage examples. It does not contain malicious or deceptive behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Python os.getenv — reads environment variable
references/conference-paper-scraping.md · code · os.getenv(
Popular HTTP library — network access
scripts/cloudflare_email_decoder.py · prose · downgraded · Got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.