write-a-prd
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the workspace files and conversation context to generate a Product Requirements Document (PRD), creating a surface for indirect instructions.
- Ingestion points: Explores the repository files and processes current conversation context as defined in the 'Process' section of SKILL.md.
- Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore potentially malicious directives embedded within the repository files or chat history.
- Capability inventory: The skill utilizes
wiki configandwiki forgeCLI commands to resolve configuration and publish artifacts to the workspace. - Sanitization: No explicit sanitization, validation, or escaping of the ingested content is specified before the information is synthesized into the final PRD.
Audit Metadata