ClawAudit verdict
email-pro-optimized
However, the skill seems to be designed for legitimate purposes, such as high-performance email processing.
⚠ 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 (5)
pip3 install — installs Python packages at runtime
SKILL.md · code · pip3 install
subprocess execution — runs system commands from Python
scripts/auto-push.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/auto-push.py · prose · downgraded · subprocess.run(
cmd,
shell=True
Python os.getenv — reads environment variable
scripts/oauth_handler.py · prose · downgraded · os.getenv(
POSTs data to external URL
scripts/providers.py · prose · downgraded · .post('https://
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
network_outnetwork_inpackage_install Is this flag fair?
Thanks — recorded.