interactive-requirements-gathering
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input through 'Type your own' options and uses this data to generate requirement documents, creating a potential surface for indirect prompt injection.
- Ingestion points: User input received via the AskUserQuestion tool and specifically via 'Option D' (Type your own) as described in SKILL.md.
- Boundary markers: No explicit instruction for the agent to use delimiters or sanitization for user-provided strings when interpolating them into generated requirements.
- Capability inventory: The skill utilizes Read, Write, Edit, and AskUserQuestion tools across its operations.
- Sanitization: No sanitization, escaping, or validation logic is defined for the custom user inputs before they are processed.
Audit Metadata