ClawAudit verdict
koan-team
The skill requires explicit human approval and seems to follow secure practices for Koan team organization.
⚠ 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 (4)
Accesses system credential store
python/koan_sdk.py · prose · downgraded · KEYCHAIN
subprocess execution — runs system commands from Python
python/koan_sdk.py · prose · downgraded · subprocess.run(
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Python urllib.request — network access
python/koan_sdk.py · prose · downgraded · urllib.request
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.
Is this flag fair?
Thanks — recorded.