to-prd
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as intended for a development automation tool. It identifies 'seams' for testing, follows ADRs, and uses project-specific terminology without exhibiting malicious behavior, obfuscation, or unauthorized data exfiltration.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its requirement to ingest and process codebase content and conversational data which may contain untrusted instructions.
- Ingestion points: Repository files and current conversation context as described in Step 1 of the skill flow.
- Boundary markers: None identified; there are no specific instructions or delimiters to prevent the agent from following commands embedded within the processed codebase or chat history.
- Capability inventory: The agent is authorized to explore the repository (file read) and post results to the project's issue tracker (external write).
- Sanitization: No validation or escaping mechanisms are described for the content before it is interpolated into the PRD template.
Audit Metadata