write-a-prd
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the GitHub CLI tool (
gh) to publish generated PRDs as repository issues when the tool is available in the environment. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection. It ingests untrusted data from both the local codebase (during repository exploration in step 2) and user responses (during the interview in step 3). These inputs are processed and interpolated into a PRD template. There are no explicit boundary markers or sanitization steps mentioned to prevent embedded instructions within the codebase or user input from manipulating the agent's final output or actions, such as writing to the filesystem or publishing to GitHub.
Audit Metadata