ux-discovery-interviewer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or dangerous capabilities were detected. The skill consists entirely of markdown instructions and YAML configuration for an AI agent persona.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interactive interviewer, ingesting user-provided product ideas as data. While it lacks formal boundary markers for this input, it has no exploitable tools (file system, network, or command execution) available, neutralizing the risk of instruction override via processed data.
- Ingestion points: User replies during the interview (SKILL.md)
- Boundary markers: Absent
- Capability inventory: None detected
- Sanitization: Absent
Audit Metadata