get-started
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of untrusted UI code which acts as a potential injection surface.
- Ingestion points: The
quick_reviewandreview_filestools are designed to receive the full content of user-provided files (React, Vue, Svelte, CSS, SwiftUI) as input (SKILL.md, sections 2 and 3). - Boundary markers: The instructions do not specify the use of delimiters or instructions for the agent to ignore hidden commands within the code files.
- Capability inventory: The skill uses tools to send data to an external service (rams.ai) and allows for the application of code patches provided by that service.
- Sanitization: There are no programmed instructions to sanitize or validate the content of the UI files before they are processed by the tool or presented to the agent.
Audit Metadata