ClawAudit verdict
clawy
The skill generates stable agent avatars and short image-driven adventure arcs, using external image-edit providers with proper credentials.
⚠ 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)
Instructs covert action — may act without user awareness
references/image-edit-playbook.md · prose · downgraded · quietly
subprocess execution — runs system commands from Python
scripts/generate_avatar.py · prose · downgraded · subprocess.check_output(
Python urllib.request — network access
scripts/generate_avatar.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/generate_avatar.py · prose · downgraded · os.environ.get(
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
Requires 1 environment variable. (1 sensitive: ONE_OF:WAVESPEED_API_KEY|OPENAI_API_KEY|GEMINI_API_KEY|NANO_API_KEY|ARK_API_KEY).
Is this flag fair?
Thanks — recorded.