prd-to-plan
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted PRD documents provided by the user without using boundary markers or sanitization, creating a surface for indirect prompt injection.
- Ingestion points: User-provided PRD in
SKILL.md(Step 1). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the PRD content.
- Capability inventory: The skill allows the agent to read the codebase and write markdown files to the
./plans/directory. - Sanitization: No input validation or sanitization is performed on the PRD text.
Audit Metadata