derisk-measurement-advisor
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as an interactive workshop guide using a standard prompt-and-response pattern. It does not perform network operations, file system modifications, or execute external code.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it accepts user-provided text (product ideas and customer roles) and interpolates this content into subsequent agent prompts.
- Ingestion points: User input is collected in Context Q1/4 and Context Q4/4.
- Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the user-provided context.
- Capability inventory: The skill lacks dangerous capabilities such as file system access, network requests, or subprocess execution, which significantly mitigates the risk of injection.
- Sanitization: No input validation or sanitization of user-provided strings is performed prior to interpolation.
Audit Metadata