limrun-detox-testing
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references configuration examples and SDK resources hosted in the official GitHub repository of the vendor, limrun-inc.
- [COMMAND_EXECUTION]: Instructions include the use of
limandnpx detoxCLI tools to manage tunnels, launch applications, and run test servers on the local machine. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where malicious data within a mobile application's UI could attempt to influence the agent's behavior during debugging.
- Ingestion points: The agent is instructed to read and analyze output from the
lim ios element-tree --id <ios-id>command, which contains untrusted strings from the application's UI hierarchy. - Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between UI data and system instructions.
- Capability inventory: The skill provides the agent with capabilities to manage network tunnels, launch applications, and delete simulator instances.
- Sanitization: The instructions do not mention sanitization or validation of the element tree output before the agent processes it.
Audit Metadata