Caveat verdict

claw-def

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

This is a minimal description of an OpenClaw security protection system with no capabilities declared and no suspicious patterns 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.

0
security
60
transparency
50
maintenance

Findings (6)

Pattern match high

Accesses .ssh directory

ZHIHU-PUBLISH.md · code · .ssh/

Pattern match high

Accesses cloud provider credentials

ZHIHU-PUBLISH.md · code · ~/.aws

Pattern match high

Accesses sensitive system files

src/file_protection.py · prose · downgraded · /etc/passwd

Pattern match high

Accesses Azure credentials directory

src/file_protection.py · prose · downgraded · ~/.azure

Pattern match high

Accesses AWS credentials file

tests/integration/test_file_protection_integration.py · prose · downgraded · ~/.aws/credentials

Pattern match medium

Opens WebSocket connection

ZHIHU-PUBLISH.md · code · WebSocket

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