ClawAudit verdict

claw-graceful-recovery

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This is a purely procedural error-recovery skill for WeChat command execution that explicitly prohibits privilege escalation, limits retries, and only performs local log writes; no network access or data exfiltration is present.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

20
security
90
transparency
90
maintenance

Findings (4)

Pattern match critical

Accesses sensitive system files

i18n-en-references/feedback-templates.md · code · /etc/hosts

Pattern match high

References sudo — requests elevated privileges

i18n-en-references/feedback-templates.md · code · sudo

Pattern match high

Accesses .ssh directory

references/feedback-templates.md · code · .ssh/

Pattern match medium

Instructs covert action — may act without user awareness

i18n-en-references/feedback-templates.md · prose · downgraded · silently

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