ux-researcher-designer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied research data in JSON format which is then processed by a script to generate personas. Malicious instructions embedded within the research data (e.g., in 'pain_points' or 'interview_insights') could influence the agent's behavior when it reviews the generated components.
  • Ingestion points: scripts/persona_generator.py (line 126) and SKILL.md (Workflow 1).
  • Boundary markers: The skill does not implement delimiters or 'ignore instructions' warnings when processing or displaying the user data.
  • Capability inventory: Command execution is used to run the persona generator script (SKILL.md).
  • Sanitization: No sanitization, validation, or escaping of user-provided content is performed before it is processed or used to generate outputs for the agent.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script to perform data analysis and persona generation.
  • Evidence: SKILL.md contains explicit instructions to run python scripts/persona_generator.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — ux-researcher-designer