android-ui-driver

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on subprocess.run to interact with the Android Debug Bridge (adb). The implementation correctly uses shlex.quote for all shell arguments to mitigate command injection risks.
  • [PROMPT_INJECTION]: The skill includes documentation alerting the AI to the risk of indirect prompt injection from third-party app content (e.g., text that says 'ignore previous instructions'). This is a defensive measure to prevent the AI from being manipulated by the data it processes.
  • [DATA_EXFILTRATION]: Screen snapshots are cached in a temporary directory using tempfile.gettempdir(). The script enforces restrictive file permissions (0o600) when creating these cache files, preventing other users on the system from reading potentially sensitive UI data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 08:45 AM
Security Audit — agent-trust-hub — android-ui-driver