spec-interview
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided feature specifications which serves as an ingestion point for untrusted data.
- Ingestion points: Review of the user's initial specification in Step 1.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate the input.
- Capability inventory: The skill utilizes the
ask_user_questiontool for clarifying information. - Sanitization: No input validation or filtering of the user's specification is performed.
Audit Metadata