generate-github-issue
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various GitHub CLI (gh) commands to manage issue creation, including checking authentication status, listing issues, creating labels, and publishing issue content.
- [COMMAND_EXECUTION]: The skill uses Git commands such as git log to inspect repository history for the purpose of language detection.
- [PROMPT_INJECTION]: The skill analyzes untrusted data from the repository (README, existing issue titles, and source code files) to determine context for new issues, creating a surface for indirect prompt injection.
- Ingestion points: Repository files (README, CLAUDE.md, configuration files) and existing issue titles retrieved via gh issue list.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within ingested data are implemented.
- Capability inventory: The skill possesses file system read access and write access to the GitHub API via the gh CLI for creating and commenting on issues.
- Sanitization: No explicit sanitization or filtering of content from the repository or GitHub API is performed prior to processing.
Audit Metadata