ClawAudit verdict
tapauth
The skill provides OAuth token and manual secret management and does not contain any malicious or deceptive behavior.
⚠ 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.
Findings (3)
Possible hardcoded credential
scripts/test-tapauth-cli.sh · prose · downgraded · token="$(run_tapauth --token google calendar.readonly 2>
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Sets world-executable permissions
scripts/tapauth.sh · prose · downgraded · chmod 700
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.