interview
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository files and conversation history to formulate its discovery strategy, which creates an ingestion surface for potential indirect prompt injection. This risk is managed through a structured verification process that requires the user to review synthesized assumptions and confirm the final intent.
- Ingestion points: The skill grounds its operations on conversation history, in-scope files, repository contents, and prior artifacts.
- Boundary markers: The process includes an inverted interview synthesis step and a final one-sentence intent confirmation to validate inferences with the user.
- Capability inventory: The skill generates text-based interview rounds and briefs; it only performs file writes if explicitly requested by the user.
- Sanitization: The skill does not explicitly describe automated sanitization or filtering of the ingested context files.
Audit Metadata