qwen-image

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation includes an installation command curl -fsSL https://cli.inference.sh | sh. This script is hosted on the official domain of the skill author (inference-sh) and is the standard method for deploying their CLI tool.
  • [EXTERNAL_DOWNLOADS]: The installation process fetches platform-specific binaries and checksums from dist.inference.sh. These resources are provided by the vendor to facilitate the skill's primary function.
  • [COMMAND_EXECUTION]: The skill requests permission to use the Bash tool, but explicitly limits the scope to the infsh command using the allowed-tools: Bash(infsh *) constraint. This follows the principle of least privilege.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided prompts and external image URIs through the reference_images parameter. While this presents a theoretical surface for indirect injection, the risk is mitigated by the structured JSON input format and the specialized nature of the image generation task.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 05:17 AM