Caveat verdict

clawguard

clawguard-secure

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

A security report reading and remediation guidance assistant that explicitly prohibits performing scans itself and forbids modifying configs without user confirmation; behavior is advisory-only and matches the stated purpose.

⚠ 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.

38
security
90
transparency
70
maintenance

Findings (5)

Pattern match high

Writes to SKILL.md — self-modifying skill

references/fix-impact-patterns.md · prose · downgraded · SKILL.md` files for file paths and Read/Write

Pattern match high

Accesses AWS credentials file

references/rule-deep-explainers.md · prose · downgraded · ~/.aws/credentials

Pattern match medium

Instructs covert action — may act without user awareness

references/rule-deep-explainers.md · prose · downgraded · silently

Pattern match medium

Accesses cloud provider credentials

references/rule-deep-explainers.md · prose · downgraded · ~/.aws

Pattern match low

Sets world-executable permissions

references/fix-impact-patterns.md · prose · downgraded · chmod 700

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