ClawAudit verdict
simmer-preflight
The skill appears to be a pre-trade readiness check. It uses credentials but for a legitimate purpose of checking trading readiness.
⚠ 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
tests/test_preflight.py · prose · downgraded · api_key = "sk_live_test
Python os.environ.get — reads environment variable
SKILL.md · code · os.environ.get(
Instructs covert action — may act without user awareness
tests/test_preflight.py · prose · downgraded · silently
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.