ClawAudit verdict
ngrok-preview
The skill provides a transparent and controlled way to generate temporary ngrok preview links for local artifacts, with clear safety boundaries and a focus on task-specific outputs.
⚠ 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 (6)
References tunneling service
SKILL.md · frontmatter · ngrok
subprocess execution — runs system commands from Python
scripts/ngrok_preview.py · prose · downgraded · subprocess.run(
HTTP request to bare IP address — common in malicious payloads
scripts/ngrok_preview.py · prose · downgraded · http://127.0.0.1
Python urllib.request — network access
scripts/ngrok_preview.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
scripts/ngrok_preview.py · prose · downgraded · shutil.copytree(
Python os.environ.get — reads environment variable
scripts/ngrok_preview.py · prose · downgraded · os.environ.get(
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.
credential_access Is this flag fair?
Thanks — recorded.