ClawAudit verdict
polymarket-brain
The skill embeds a specific Discord webhook URL in its content and automatically pushes fetched news and AI analysis to that external destination, creating an unusual data-exfiltration-adjacent pattern where third-party content is relayed to a hardcoded external endpoint without explicit user confirmation each cycle.
⚠ 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.
Permission integrity
network_out
package_install
Findings (7)
Pipe to python — executes piped content as Python code
RESTART_GUARANTEE.md · prose · downgraded · | Python
Python urllib.request — network access
SKILL.md · code · urllib.request
References webhook/callback URL
SKILL.md · code · webhook_url
subprocess execution — runs system commands from Python
polymarket_brain_orchestrator_FIXED.py · prose · downgraded · subprocess.run(
POSTs data to external URL
TROUBLESHOOTING.md · code · .post('https://
Python os.environ.get — reads environment variable
polymarket_brain_orchestrator.py · prose · downgraded · os.environ.get(
Python os.getenv — reads environment variable
scripts/orchestrate.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C/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.
package_installnetwork_innetwork_out Is this flag fair?
Thanks — recorded.