prd-writer
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a logical and structured workflow for business analysis and documentation. It includes multiple manual checkpoints (Step 3, 4, and 7) where the agent is required to seek user validation and confirmation, which significantly reduces the risk of autonomous malicious actions.
- [SAFE]: Although the skill utilizes file system tools (search_file_content, read_file, write_file) to process project data, it does not include any network-capable tools or instructions to communicate with external servers, effectively mitigating data exfiltration risks.
- [SAFE]: All file operations are confined to standard documentation formats (.md) and follow a predictable naming convention based on the project context. No attempts at privilege escalation, persistence, or system-level modification were identified.
- [SAFE]: A thorough review of the text in all files (SKILL.md, assets/PRD-Template.md, and workflow-and-best-practices.md) revealed no hidden instructions, obfuscated URLs, or prompt injection attempts designed to bypass AI safety guardrails.
Audit Metadata