qwen-image-pro

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI tool to interact with the image generation service. This tool is provided by the vendor and used as intended for service interaction.
  • [EXTERNAL_DOWNLOADS]: The skill references the inferencesh Python library and the inference-sh/skills package for installation. These are official vendor-managed resources.
  • [PROMPT_INJECTION]: The skill accepts user-defined prompts for image generation, creating a surface for indirect prompt injection.
  • Ingestion points: The prompt parameter in the infsh app run bash command and Python SDK calls.
  • Boundary markers: No specific boundary markers or escape sequences are implemented for the prompt string.
  • Capability inventory: The skill possesses the Bash(infsh *) capability to send input to a remote AI model.
  • Sanitization: The skill does not perform local sanitization of the input prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 11:52 PM
Security Audit — agent-trust-hub — qwen-image-pro