Caveat verdict
authorization-first
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
A safety-enforcement skill (written in Chinese) that requires explicit user authorization before any file modification, command execution, or external action; explicitly designed to add human oversight, not bypass it.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
80
security
70
transparency
70
maintenance
Findings (1)
Pattern match high
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.