Caveat verdict

eridian-carapace

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

Agent security hardening skill documenting 8 attack vector defenses and prompt injection countermeasures; purely defensive guidance with no credentials, network access, or executable sinks in the content.

⚠ 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.

60
security
90
transparency
70
maintenance

Findings (2)

Pattern match critical

Prompt injection — tries to override agent instructions

references/attack-vectors.md · code · Ignore previous instructions

Pattern match medium

Accesses .ssh directory

references/attack-vectors.md · prose · downgraded · .ssh/

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