ralph-tui-prd
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a pure text-generation prompt. It guides the AI agent through a series of clarifying questions to produce a structured Product Requirements Document. It does not utilize any execution tools, perform network operations, or access sensitive files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided feature descriptions to generate documentation. However, it lacks any dangerous capabilities that would allow for exploitation via prompt injection. 1. Ingestion points: User-provided feature descriptions and iterative responses to clarifying questions in SKILL.md. 2. Boundary markers: The generated PRD output is explicitly delimited by [PRD] and [/PRD] markers. 3. Capability inventory: None. The skill does not invoke any tools for file writing, command execution, or network access. 4. Sanitization: Not present, as the skill's primary function is text documentation generation rather than execution.
Audit Metadata