specialist-design-ux-researcher

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-controlled input directly into a sub-agent's prompt without adequate safety measures.
  • Ingestion points: The '{the user's question}' placeholder in the Agent tool call in SKILL.md.
  • Boundary markers: Absent; user input is not enclosed in delimiters or accompanied by instructions to ignore embedded instructions.
  • Capability inventory: The skill utilizes the Agent tool to spawn and delegate tasks to another specialized agent.
  • Sanitization: No input validation or filtering is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-design-ux-researcher