ux-researcher-designer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing external user research data.
- Ingestion points: Untrusted data enters via JSON files processed by scripts/persona_generator.py.
- Boundary markers: The generated output lacks explicit delimiters or instructions to the agent to disregard instructions within the research data.
- Capability inventory: The skill performs data aggregation and persona synthesis; it does not possess network or broad file system permissions.
- Sanitization: There is no evidence of sanitization of user-provided strings before report generation.
Audit Metadata