qinghu-model-outfit-swap

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads Node.js binaries and checksum files from nodejs.org. This is a well-known service and the skill includes an explicit verification step using sha256sum to ensure the downloaded file has not been tampered with.
  • [COMMAND_EXECUTION]: Executes the qhkit command to perform image generation tasks. The setup instructions include extracting archives and managing environment variables, which are standard operations for tool installation.
  • [PERSISTENCE]: Instructs the user on how to persist PATH changes in ~/.bashrc. This is a routine configuration step for ensuring development tools remain accessible across shell sessions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided image paths and textual prompts. While this represents a standard injection surface for LLM-integrated tools, it does not exhibit specific vulnerabilities beyond the inherent risks of processing natural language inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 04:09 PM