qa
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gh issue createcommand to programmatically file bug reports on GitHub repositories. - [EXTERNAL_DOWNLOADS]: The skill communicates with GitHub's official services via the
ghcommand-line interface to file issues. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user descriptions to generate external content.
- Ingestion points: Conversational user input describing problems in
SKILL.md. - Boundary markers: Absent; the skill does not define specific delimiters for the interpolated user content.
- Capability inventory: GitHub write access via
gh issue createand codebase read access via a background 'Explore' agent. - Sanitization: The instructions require the agent to reformat user input into durable templates and explicitly prohibit including sensitive internal details like file paths or line numbers.
Audit Metadata