intent-interview
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill captures untrusted user input and transforms it into technical specifications for downstream agents, creating a path for potential instruction injection. Ingestion points: User input in Phase 1-4. Boundary markers: None in templates. Capability inventory: Generating Markdown files and optional repository interaction. Sanitization: None provided.
- No Code (SAFE): This skill contains only instructional text and no executable scripts or system-level configuration.
Audit Metadata