adb-cli

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include the use of npx -p android-debug-bridge-mcp adb-agent, which fetches and executes the specified package from the official NPM registry if it is not present on the system. This package corresponds to the skill author's verified namespace.\n- [COMMAND_EXECUTION]: The skill enables the agent to execute shell commands on the connected Android device via the system shell command. This grants the agent broad control over the device's operating system environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from a device's accessibility tree and system logs, which are external and potentially untrusted sources.\n
  • Ingestion points: Data enters the agent's context through adb-agent ui dump and adb-agent system logcat.\n
  • Boundary markers: The instructions do not define boundary markers or delimiters to help the agent distinguish between its instructions and the data being processed.\n
  • Capability inventory: The skill has high-privilege capabilities including file management (push, pull), app installation (install), and device shell access (system shell).\n
  • Sanitization: No sanitization or filtering of the device-side data is described before it is passed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 09:08 PM