prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the official GitHub CLI (gh) to view and create issues. These operations are essential to the skill's intended workflow and are conducted within the context of the user's repository.
- [PROMPT_INJECTION]: The skill ingests external data by viewing PRDs and their comments. The risk of indirect prompt injection is mitigated by the design of the workflow, which requires the agent to present a proposed breakdown to the human user for approval (Step 4) before creating any issues (Step 5). This provides a necessary safety checkpoint for content retrieved from untrusted external sources.
Audit Metadata