qa
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gh issue createcommand to interact with GitHub. This is the primary intended function of the skill to automate issue reporting. - [PROMPT_INJECTION]: The skill incorporates untrusted user-provided bug descriptions into generated GitHub issues, which represents an indirect prompt injection surface.
- Ingestion points: User narratives and problem descriptions collected during the interactive session (SKILL.md).
- Boundary markers: Absent; user input is directly interpolated into structured Markdown templates.
- Capability inventory: Execution of
gh issue createto write data to external GitHub repositories. - Sanitization: No explicit sanitization, escaping, or validation of user-provided content is defined before the issue is created.
Audit Metadata