qwen-image-pro
Fail
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides a 'Quick Start' command (
curl -fsSL https://cli.inference.sh | sh) that downloads a script from a remote URL and executes it immediately. This is a dangerous pattern that allows for arbitrary code execution from a source outside of the trusted organization list. - [COMMAND_EXECUTION]: The skill is configured with
allowed-tools: Bash(infsh *), which grants it permission to execute theinfshcommand with any arguments. This capability is used to interact with remote image generation models and handle local files. - [PROMPT_INJECTION]: The skill processes user-provided data via the
promptandnegative_promptparameters. These inputs are passed directly to theinfshtool without sanitization or clear boundary markers, creating a surface where malicious instructions embedded in user data could potentially be executed by the agent or model.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata