Caveat verdict
agent-dlp
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
A local data-loss-prevention tool that detects prompt injection and filters sensitive output; it operates entirely locally with no network egress and credential_access is used defensively to detect and block leakage, not to exfiltrate.
⚠ 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.
70
security
40
transparency
70
maintenance
Findings (1)
Pattern match critical
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.