ClawAudit verdict
page-behavior-audit
The skill appears to be a browser automation and content safety policy enforcement tool, which uses legitimate capabilities for its 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. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
Findings (3)
References webhook/callback URL
SKILL.md · frontmatter · WEBHOOK_URL
References sudo — requests elevated privileges
install.sh · prose · downgraded · sudo
Accesses shell history/config
install.sh · prose · downgraded · ~/.zshrc
Permissions & capabilities
No declared permissions — minimal attack surface.
network_innetwork_out Is this flag fair?
Thanks — recorded.