gr-user-interview
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent processes external, untrusted data to influence product development and issue tracking.
- Ingestion points: User interview transcripts, screen recordings, and usage data mentioned in
SKILL.mdandreferences/templates.md. - Boundary markers: The instructions do not specify any delimiters or warnings to treat transcript content as untrusted or to ignore embedded instructions within user quotes.
- Capability inventory: The skill is designed to influence automated issue creation (e.g., in Linear) and product roadmap decisions based on AI-summarized feedback.
- Sanitization: No evidence of sanitization, filtering, or escaping of user-provided transcript content is present in the methodology.
Audit Metadata