design-ux
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external user interfaces, which represents a surface for indirect prompt injection. \n
- Ingestion points: The agent processes rendered UI artifacts and interaction traces as described in the procedure section of SKILL.md.\n
- Boundary markers: Absent; the instructions do not provide specific delimiters or warnings to disregard instructions embedded within the processed UI elements.\n
- Capability inventory: The skill directs the agent to perform rendering, task tracing, and scoring actions based on visual input in SKILL.md.\n
- Sanitization: Absent; the skill does not specify any sanitization or validation of text content found within the target UIs.\n- [EXTERNAL_DOWNLOADS]: The skill references usability guidelines and interaction patterns from Vercel Labs' official GitHub repository. This is an informational reference to a well-known service.
Audit Metadata