ux-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, user-provided visual and behavioral inputs, such as HTML demos, Figma links, and wireframes, to generate structured documentation. This processing of potentially attacker-controlled content creates an attack surface where instructions hidden within the source data could influence the agent's output or actions.
- Ingestion points: Processes user-provided Figma designs, HTML demos, screenshots, videos, and wireframes (SKILL.md).
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded commands within the analyzed data.
- Capability inventory: The skill writes files to the local filesystem, specifically the
prd/directory (SKILL.md). - Sanitization: Absent; there is no mention of sanitizing or validating external input before it is analyzed and used to generate content written to disk.
Audit Metadata