to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI tool (
gh) to interact with remote repositories. Specifically, it executesgh issue viewto retrieve existing issue content andgh issue createto generate new work items based on the analysis. - [PROMPT_INJECTION]: The skill possesses a surface for Indirect Prompt Injection (Category 8) through the ingestion of external data. Ingestion points: Data is fetched from GitHub issues and comments via the
gh issue view <number> --commentscommand documented inSKILL.md. Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the fetched PRD content. Capability inventory: The agent has the ability to create new GitHub issues (gh issue create) and explore the codebase. Sanitization: No explicit sanitization or validation of the fetched PRD content is performed before it is used to draft or create issues.
Audit Metadata