issue-creation
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to list, create, and edit issues. These are standard operations for repository management and do not involve unauthorized command execution. - [DATA_EXFILTRATION]: No hardcoded credentials or sensitive file paths are present. All repository references point to the author's own GitHub organization and well-known services (GitHub).
- [PROMPT_INJECTION]: The skill processes user-provided content (bug descriptions, feature requests) to generate GitHub issues, creating an indirect prompt injection surface.
- Ingestion points: SKILL.md defines fields for user input like "Bug Description" and "Proposed Solution".
- Boundary markers: Absent. The examples show direct interpolation of content into the
--bodyflag of theghcommand. - Capability inventory: Execution of
gh issue createandgh issue list(SKILL.md). - Sanitization: Not explicitly defined in the skill instructions; however, the impact is limited to GitHub issue content.
Audit Metadata