using-github-issues
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue titles, bodies, and comments, creating a surface for indirect prompt injection.
- Ingestion points: Commands such as gh issue list and gh issue view in references/gh-cli-commands.md retrieve external content.
- Boundary markers: Not explicitly defined; there are no instructions to use specific delimiters or ignore embedded instructions when reading existing issues.
- Capability inventory: The skill can create, edit, close, and comment on issues, and includes references for shell execution via xargs.
- Sanitization: No specific sanitization or escaping of retrieved content is defined.
- [COMMAND_EXECUTION]: The references/gh-cli-commands.md file provides examples of using xargs to dynamically construct shell commands for batch operations. While these examples use structured data (issue numbers), they represent a point where external data is interpolated into command lines.
Audit Metadata