requirements-ai
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (ideas, features, business rules) and interpolates them into generated Markdown documents.
- Ingestion points: User input collected during the 10-stage workflow described in
SKILL.md. - Boundary markers: Absent. The instructions do not define specific delimiters or guidelines to help the agent distinguish between user-provided data and potentially malicious embedded instructions.
- Capability inventory: The skill is designed to write multiple files to the filesystem (
PRD.md,TRD.md,APP_FLOW.md,DESIGN_BRIEF.md,BACKEND_SCHEMA.md,IMPLEMENTATION_PLAN.md). - Sanitization: Absent. The skill does not instruct the agent to sanitize or escape input before including it in the output files.
Audit Metadata