ClawAudit verdict

automatic-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Meta-skill for automated skill generation and publishing pipeline using GitHub CLI and ClawHub with explicitly scoped tokens (GITHUB_TOKEN, CLAWHUB_TOKEN); all actions match the stated autonomous skill-factory purpose.

⚠ 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.

25
security
80
transparency
80
maintenance

Findings (7)

Pattern match high

Writes to SKILL.md — self-modifying skill

scripts/create.js · prose · downgraded · SKILL.md name, description, all section headings and body text: write

Pattern match high

Possible hardcoded credential

scripts/scan-fix.js · prose · downgraded · token = "ghp_abc123...

Pattern match medium

Accesses shell history/config

SKILL.md · prose · downgraded · ~/.zshrc

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Instructs covert action — may act without user awareness

scripts/review.js · prose · downgraded · silently

Pattern match low

Base64 encoding/decoding

data/safety-patterns.json · prose · downgraded · BASE64_DECODE

Pattern match low

Accesses sensitive environment variables

scripts/scan-fix.js · prose · downgraded · process.env.GITHUB_TOKEN

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