ClawAudit verdict
claude-code-model
Configuration skill for switching Claude Code to custom model providers; credential_access reads API keys to write into Claude Code config files, the stated legitimate 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.
Permission integrity
credential_access
Findings (2)
Possible hardcoded credential
scripts/configure_model.py · prose · downgraded · API_KEY="{api_key}
subprocess execution — runs system commands from Python
scripts/configure_model.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.