ClawAudit verdict
feynman-lobster
The skill reads and writes files, which may be considered sensitive. However, it does not appear to have any malicious intent.
⚠ 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)
Uses eval() — can execute arbitrary code
instructions/feynman.md · prose · downgraded · eval(
References agent memory files
README.md · code · MEMORY.md
Python os.environ.get — reads environment variable
scripts/feynman_api.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
Is this flag fair?
Thanks — recorded.