ClawAudit verdict
signal-pipeline
The skill appears to be a marketing intelligence pipeline that aggregates signals from multiple sources and generates content. It uses legitimate capabilities like file storage and network access for its intended purpose.
⚠ 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
package_install
Findings (3)
subprocess execution — runs system commands from Python
newsletter_monitor.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
newsletter_monitor.py · prose · downgraded · subprocess.run(
f"gog gmail search '{query} newer_than:30d' --max 5
Python urllib.request — network access
x_monitor.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.
package_install Is this flag fair?
Thanks — recorded.