skills/inf-sh/skills/qwen-image-2/Gen Agent Trust Hub

qwen-image-2

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI tool to interface with Alibaba image generation models. The execution scope is defined in the skill's frontmatter configuration.- [EXTERNAL_DOWNLOADS]: The instructions reference the installation of the infsh CLI and additional skills from the vendor's official GitHub repository and via npx commands.- [PROMPT_INJECTION]: The skill accepts user-provided text prompts and image URLs, which constitutes an indirect prompt injection surface typical for generative AI tools.
  • Ingestion points: User data enters via the prompt and reference_images parameters in the JSON input for the infsh command.
  • Boundary markers: The skill uses JSON formatting to structure the input data.
  • Capability inventory: The primary capability is executing the infsh tool to run remote AI applications.
  • Sanitization: There is no explicit sanitization described for the user-supplied prompt text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:10 PM
Security Audit — agent-trust-hub — qwen-image-2