skills/mattpocock/skills/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted conversational data from users to generate GitHub issues and direct codebase exploration. * Ingestion points: User-provided bug descriptions and reproduction steps. * Boundary markers: None provided to distinguish user data from instructions. * Capability inventory: Uses 'gh issue create' for remote writes and 'Explore' subagents for codebase reads. * Sanitization: No evidence of input validation or sanitization before interpolation into issue templates.
  • [COMMAND_EXECUTION]: Utilizes the GitHub CLI tool ('gh') to perform state-changing operations on external repositories based on user-supplied information.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 08:28 PM