Caveat verdict

sentinel-shield

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

Runtime security monitoring for OpenClaw agents with behavior consistent with its stated purpose; Telegram alerts are optional and user-configured.

⚠ 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.

13
security
90
transparency
80
maintenance

Findings (7)

Pattern match critical

Accesses sensitive system files

SKILL.md · code · /etc/passwd

Pattern match high

Accesses .ssh directory

SKILL.md · code · .ssh/

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

Pattern match medium

References sudo — requests elevated privileges

scripts/injectionScanner.js · prose · downgraded · sudo

Pattern match low

Sets world-executable permissions

scripts/injectionScanner.js · prose · downgraded · chmod 777

Pattern match low

Changes file ownership

scripts/injectionScanner.js · prose · downgraded · chown

Pattern match low

References tunneling service

scripts/injectionScanner.js · prose · downgraded · ngrok

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_store

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API