prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, prompt injections, or obfuscation techniques were detected in the skill definition.
- [COMMAND_EXECUTION]: The codebase exploration step is a standard read-only activity for AI agents to gain context before proposing task breakdowns.
- [DATA_EXPOSURE]: The skill interacts with the Linear project management tool using Model Context Protocol (MCP) to read PRDs and write issues, which aligns with its primary stated purpose.
- [SAFE]: The workflow incorporates a human-in-the-loop (HITL) step (Step 4), which requires user approval for the proposed issue list before the agent executes write operations, mitigating risks of automated data corruption or indirect injection.
Audit Metadata