qa
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements an automated workflow that processes untrusted user input into persistent GitHub issues.
- Ingestion points: Conversational descriptions of bugs and issues provided by the user in
SKILL.md. - Boundary markers: Absent. There are no delimiters or specific instructions to prevent the agent from following instructions embedded within the user's report.
- Capability inventory: The skill uses
gh issue createfor network write operations and a sub-agent (Explore) for codebase analysis. - Sanitization: Absent. The instructions explicitly direct the agent to skip human review ("Do NOT ask the user to review first — just file and share URLs"), which removes a critical checkpoint for validating the content being published.
- [COMMAND_EXECUTION]: The skill uses command-line tools to interact with external services.
- Evidence: The skill instructions specify using
gh issue createto submit data to GitHub repositories based on content generated from user discussions.
Audit Metadata