requirement-refine
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a well-documented and professional tool for requirement engineering. It uses structured interviews and multiple validation 'waves' to ensure the quality and completeness of the generated documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill inherently handles untrusted external data (raw requirements, tickets, emails) as part of its core function. This creates a standard ingestion surface for potential indirect prompt injection.
- Ingestion points: Raw requirement files stored in the
references/directory of the SRS folder. - Boundary markers: The instructions guide the agent to interpret all input content to define scope, but do not explicitly use delimiters to separate user data from system instructions.
- Capability inventory: The skill performs file writes to create SRS documentation and wireframes, and it can invoke other agent skills for technical research and project definition.
- Sanitization: There are no explicit content filtering or sanitization steps mentioned for the raw inputs.
Audit Metadata