ClawAudit verdict
ez-google
The skill provides agent-friendly Google Workspace tools with hosted OAuth, but may request elevated access to Google accounts.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
<script> tag in markdown โ potential code injection
SKILL.md ยท prose ยท downgraded ยท <script>
Python os.environ.get โ reads environment variable
scripts/auth.py ยท prose ยท downgraded ยท os.environ.get(
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.