ClawAudit verdict
pure-wan-fridge-gourmet
Fridge-photo-to-recipe AI generation skill with no declared capabilities and no network exfiltration; all behavior is local image analysis and recipe generation matching the stated purpose.
⚠ 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/examples.md · code · API_KEY="your-wan-api-key-here
Python os.environ.get — reads environment variable
scripts/generate_gourmet.py · prose · downgraded · os.environ.get(
POSTs data to external URL
scripts/generate_gourmet.py · prose · downgraded · .post(
"https://
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.