skills/subsy/ralph-tui/ralph-tui-prd/Gen Agent Trust Hub

ralph-tui-prd

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection via Command Pass-through.
  • Ingestion point: The skill explicitly asks the user to provide 'quality gate' shell commands during the iterative questioning phase.
  • Boundary markers: The PRD is wrapped in '[PRD]' markers, but the user-provided commands are not sanitized before inclusion.
  • Capability inventory: The skill itself has no execution capabilities, but its output is designed for 'ralph-tui' tools that automate execution based on the generated PRD.
  • Sanitization: No validation or filtering is performed on user-specified 'Other' commands, allowing for the injection of malicious shell instructions into the final PRD document.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM