ClawAudit verdict

android-agent

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

A documented ADB-based Android phone automation skill using GPT-4o vision via DroidRun; all described operations (screenshots, tap/type/swipe via ADB) are transparent device-control actions consistent with the stated purpose of automating phone tasks.

⚠ 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.

58
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Downloads executables from external URLs

SKILL.md · prose · downgraded · Download from https://

Pattern match medium

subprocess execution — runs system commands from Python

scripts/run-task.py · prose · downgraded · subprocess.run(

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · Got

Pattern match low

Python os.environ.get — reads environment variable

scripts/run-task.py · prose · downgraded · os.environ.get(

Pattern match low

References agent configuration files

scripts/run-task.py · prose · downgraded · AgentConfig

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.

package_install

Is this flag fair?

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