ui-review
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes 'bin/rails routes' to discover application endpoints. This is a standard development command used to map the application surface for auditing purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of rendered HTML and discovered routes from the application. While this constitutes an attack surface, the agent's instructions are focused on structural analysis of CSS classes and HTML tags, and it does not perform sensitive operations based on the content of the data.
Audit Metadata