ClawAudit verdict
wecom-add-friend
The skill automates adding friends on WeCom, which may lead to unintended interactions or spam if not properly monitored.
⚠ 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 (2)
subprocess execution — runs system commands from Python
bin/wecom_auto_add.py · prose · downgraded · subprocess.check_output(
subprocess with shell=True — command injection vector
bin/wecom_auto_add.py · prose · downgraded · subprocess.check_output("tasklist | findstr WXWork.exe", shell=True
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 system binary.
Is this flag fair?
Thanks — recorded.