Caveat verdict
agent-firewall
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Defines filters to block injections and redact secrets; operates as a protective layer, not a threat.
⚠ 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
70
maintenance
Findings (1)
Pattern match high
Possible prompt injection — attempts to redefine agent identity
SKILL.md · code · you are now
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.