ClawAudit verdict

zhiyierxing-auto-phone

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill requires access to various tools and environment variables, which could be a concern if not properly managed.

⚠ 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.

63
security
60
transparency
70
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

scripts/run_phone_task.sh · prose · downgraded · API_KEY="${MODEL_API_KEY:-}

Pattern match medium

subprocess execution — runs system commands from Python

scripts/check_android_ready.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

scripts/check_skill_ready.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/deploy_open_autoglm.py · prose · downgraded · shutil.rmtree(

Pattern match low

Python urllib.request — network access

scripts/verify_open_autoglm.py · prose · downgraded · urllib.request

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 3 environment variables. (1 sensitive: MODEL_API_KEY).

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API