ClawAudit verdict

foundry

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

The skill researches documentation and writes new capabilities into itself, which is unusual and may pose risks if not properly controlled.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

73
security
70
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (2)

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md ยท prose ยท downgraded ยท ~/.openclaw/openclaw.json

Pattern match low

Makes HTTP request to external URL

SKILL.md ยท code ยท fetch(`https://

Permissions & capabilities

Requires 1 system binary.

network_innetwork_out

Is this flag fair?

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