prd-to-td
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external requirements documents which could contain indirect prompt injections.
- Ingestion points: User-provided PRD files or text input as described in SKILL.md.
- Boundary markers: Employs a 'Three-Pass Analysis' methodology in references/analysis-guide.md to extract and validate information before action.
- Capability inventory: Interaction with the td CLI tool (create, log, ws) and file system access to ~/.claude/plans/.
- Sanitization: Instructions focus on data extraction and mapping; the agent is responsible for ensuring extracted strings are safely used in CLI arguments.
- [COMMAND_EXECUTION]: The skill generates and executes shell commands to interact with the td CLI utility.
- Evidence: SKILL.md Step 5 explicitly details the use of td create, td log, and td ws commands for issue and session management.
Audit Metadata