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?
Thanks — recorded.