ux-researcher-designer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user research data, such as interview quotes and pain points, which could potentially contain malicious instructions.
- Ingestion points: Untrusted data enters the agent context through the JSON input for the
persona_generator.pyscript and raw research notes used during the synthesis workflow. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the research data.
- Capability inventory: Analysis of the skill's tool,
scripts/persona_generator.py, confirms it lacks dangerous capabilities; it does not perform network operations, file writes, or subprocess execution. It is restricted to string manipulation and basic data aggregation. - Sanitization: The persona generator uses standard JSON serialization for its structured output format, providing inherent protection against some forms of data confusion.
Audit Metadata