write-a-prd
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's behavior is consistent with its stated purpose of assisting in product planning and codebase exploration. No evidence of malicious intent, unauthorized data exfiltration, or unsafe command execution was found.
- [PROMPT_INJECTION]: Analysis of indirect prompt injection surfaces confirms the skill reads untrusted data from repository files and user input to populate the Linear issue template. This is a necessary component of its primary function and is treated as safe in this context.
- Ingestion points: Repository exploration (Step 2) and user interview data (Step 1, 3).
- Boundary markers: Uses markdown tags () to define output structure.
- Capability inventory: Tools for listing teams and saving issues in Linear (mcp__linear-server__list_teams, mcp__linear-server__save_issue).
- Sanitization: No explicit content sanitization logic is present for data ingested from the repository.
Audit Metadata