mobilewright-cli

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with mobile devices and simulators, including installing applications via the app-install command, launching activities, and performing UI actions such as tap, fill, and swipe.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from mobile application user interfaces and device logs, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: Untrusted data enters the agent context through the output of mobilewright-cli snapshot, find, and logs commands as described in SKILL.md. 2. Boundary markers: No specific boundary markers, delimiters, or instructions to ignore embedded content are identified in the provided usage patterns. 3. Capability inventory: The skill has access to shell execution via the Bash tool and local file system writes to the .mobilewright-cli/ directory. 4. Sanitization: The documentation does not specify any sanitization, escaping, or validation mechanisms for the content retrieved from device screens or system logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 05:01 PM