ClawAudit verdict
free-model-finder
Model discovery and configuration skill that queries public APIs for free AI models and writes results to the local openclaw.json config; all network access and file writes are documented and consistent with the stated cost-optimization 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
SKILL.md · code · API_KEY="sk-or-v1-...
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Python os.getenv — reads environment variable
scripts/main.py · prose · downgraded · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.