Caveat verdict
kinthai-self-improving-user
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill is designed to capture user corrections, preferences, and errors to improve the AI's performance. It does not contain any malicious or deceptive behavior.
⚠ 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
90
transparency
80
maintenance
Findings (1)
Pattern match high
Writes to SKILL.md — self-modifying skill
hooks/openclaw/HOOK.md · prose · downgraded · SKILL.md instructions to write
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Is this flag fair?
Thanks — recorded.