ralph-tui-prd
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill facilitates a workflow where untrusted user input (shell commands for 'Quality Gates') is embedded into a PRD document meant for automated execution by the ralph-tui tool.
- Ingestion points: User responses to the iterative clarifying questions, specifically regarding quality commands.
- Boundary markers: The final output is wrapped in [PRD] markers, but there is no instruction to validate or sanitize the shell commands gathered from the user.
- Capability inventory: The skill itself does not execute code, but the downstream tool ralph-tui is explicitly described as an orchestration tool that performs automated execution of these requirements.
- Sanitization: The skill lacks any instruction to sanitize, escape, or verify the safety of user-provided strings before adding them to the final PRD.
- [Metadata] (SAFE): The skill metadata correctly describes its purpose and does not contain any deceptive or malicious patterns.
Audit Metadata