ux-paths-native
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase files ('reading its code') to discover application features, which represents a surface for indirect prompt injection. \n- Ingestion points: Source code files of the native macOS/iOS application being analyzed. \n- Boundary markers: The instructions do not provide specific delimiters to isolate the code being analyzed from the agent's instructions. \n- Capability inventory: The agent's tasks are limited to generating documentation, user journey stories, and discovery catalogs. \n- Sanitization: No methods for sanitizing or escaping content retrieved from the codebase are defined in the instructions.
Audit Metadata