ClawAudit verdict
google-web-search
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill enables grounded question answering by executing the Google Search tool within Gemini models for real-time 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.
98
security
60
transparency
70
maintenance
Findings (1)
Pattern match low
Python os.environ.get — reads environment variable
scripts/example.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.