Caveat verdict

agent-harness-architect

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Collects user input to produce configuration files; does not exfiltrate or execute unsafe code.

⚠ 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.

90
security
100
transparency
90
maintenance

Findings (1)

Pattern match medium

References agent configuration files

SKILL.md · code · CLAUDE.md

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