Caveat verdict

guardian-wall

guardian-wall-azzar

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

Prompt injection defense skill that sanitizes external content; behavior is explicitly protective and transparent with no suspicious network usage.

⚠ 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.

30
security
90
transparency
70
maintenance

Findings (3)

Pattern match critical

Prompt injection — tries to override agent instructions

SKILL.md · frontmatter · ignore previous instructions

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

references/patterns.md · prose

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

scripts/sanitize.py · prose · downgraded · you are now

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