ClawAudit verdict
internal-admin-playwright
The skill automates internal admin tasks with Playwright, which may pose risks if not properly authorized.
⚠ 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 (5)
Possible hardcoded credential
debug/login_test.py · prose · downgraded · PASSWORD = "wulongcha
subprocess execution — runs system commands from Python
scripts/run.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/vpn_l2tp.py · prose · downgraded · subprocess.run(cmd, shell=True
Uses XMLHttpRequest — network access
scripts/review_comments.py · prose · downgraded · XMLHttpRequest
Python os.getenv — reads environment variable
scripts/run.py · prose · downgraded · os.getenv(
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.
Is this flag fair?
Thanks — recorded.