ClawAudit verdict
Codex Hook
codex-hook
The skill executes scripts which could potentially be used to exfiltrate information.
⚠ 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
package_install
Findings (3)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/.env
Possible hardcoded credential
SKILL.md · prose · downgraded · TOKEN="your-bot-token
References webhook/callback URL
SKILL.md · prose · downgraded · WEBHOOK_URL
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.