ClawAudit verdict
merchantguard
The skill provides security scanning, adversarial testing, compliance scoring, and certification for AI agents handling payments or sensitive data, which seems legitimate and transparent.
⚠ 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
package_install
Findings (3)
Accesses system credential store
guard.py · prose · downgraded · keychain
Python os.environ.get — reads environment variable
guard.py · prose · downgraded · os.environ.get(
References tunneling service
guard.py · prose · downgraded · ngrok
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inpackage_installnetwork_out Is this flag fair?
Thanks — recorded.