ClawAudit verdict

skill-editor

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

Style guide for creating AgentSkills SKILL.md files; purely instructional meta-skill with no credential access or network calls.

⚠ 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.

70
security
100
transparency
80
maintenance

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN: "API Token,说明配置方式

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