ClawAudit verdict
roundtable-pai
The skill involves running a controller script with user input, which may lead to security issues if not properly sanitized, and has strict security boundaries that need to be respected.
⚠ 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 (5)
Uses eval() — can execute arbitrary code
tests/test_controller.py · prose · downgraded · eval(
Uses exec() — may execute shell commands
tests/test_controller.py · prose · downgraded · exec(
os.system/popen — direct OS command execution
tests/test_controller.py · prose · downgraded · os.system(
Popular HTTP library — network access
references/personas/taylorswift.md · prose · downgraded · Got
Python urllib.request — network access
tests/test_controller.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.