qa
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to gather user feedback and translate it into GitHub issues. This behavior aligns with the provided description and intent.
- [COMMAND_EXECUTION]: The skill utilizes the 'gh issue create' command. This is a standard and expected operation for a tool designed to manage GitHub issues.
- [DATA_EXPOSURE]: The instructions specifically advise the agent against including internal implementation details, such as file paths or line numbers, in the generated issues. This practice helps prevent the unintentional exposure of internal repository structure in public issue trackers.
- [PROMPT_INJECTION]: The skill ingests untrusted user input (bug reports) and passes it to an exploration agent. While this creates a surface for indirect prompt injection, the skill's instructions focus on clarification and translation into structured behavioral reports rather than command execution. No explicit bypass or override instructions were detected.
Audit Metadata