Skills
Navigate
skills/whytryharder/skills/qwen-image-2-pro/Gen Agent Trust Hub

qwen-image-2-pro

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied text to generate images, which serves as a surface for indirect prompt injection.\n
  • Ingestion points: The prompt and negative_prompt fields in the JSON input structures within SKILL.md.\n
  • Boundary markers: User inputs are encapsulated within JSON objects passed to the command-line tool.\n
  • Capability inventory: The skill is configured to use the belt CLI tool via Bash.\n
  • Sanitization: Input filtering and safety protocols are managed by the inference.sh platform.\n- [EXTERNAL_DOWNLOADS]: The skill references the belt CLI and the inferencesh Python SDK, providing links to the vendor's official GitHub repository and documentation for installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — qwen-image-2-pro