Caveat verdict

agency-client-reporting

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

This is a pure documentation skill for generating client reports and QBR narratives with no network access, no credentials, and no external calls; all content is prompt templates and report format specifications.

⚠ 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.

68
security
80
transparency
80
maintenance

Findings (2)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

prompts/04_renewal_upsell_proposal.md · prose

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · got

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