ralph-tui-prd
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): This skill defines an attack surface by ingesting untrusted user input (feature descriptions) and interpolating it into a structured PRD output.
- Ingestion points: Feature descriptions provided by the user in Step 1.
- Boundary markers: The skill uses
[PRD]...[/PRD]tags for the output, but lacks explicit delimiters or 'ignore' instructions for the initial user input. - Capability inventory: The skill itself has no capabilities (no subprocess calls, file writes, or network ops). It is purely a text generator.
- Sanitization: No sanitization or validation of the user input is performed before it is included in the PRD.
- [Command Execution] (SAFE): Although the skill mentions commands like
pnpm typecheckandnpm run lint, these are included as text examples for the AI to put into a document. The skill does not attempt to execute these commands. - [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected.
Audit Metadata