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

qwen-image-2-pro

Warn

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation directs the user to install the belt-sh/cli package and points to installation instructions hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.- [REMOTE_CODE_EXECUTION]: The skill's primary functionality is dependent on executing the belt CLI tool, which is a third-party external dependency.- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection due to how it handles external data.
  • Ingestion points: The skill ingests a prompt string and an array of reference_images URIs from user-provided inputs.
  • Boundary markers: No delimiters or isolation instructions are present to distinguish untrusted data from system instructions.
  • Capability inventory: The skill is granted access to the Bash tool to run the belt CLI, which interacts with external inference servers.
  • Sanitization: There is no evidence of sanitization or validation for the prompt text or image URIs prior to their use in CLI operations.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 23, 2026, 06:04 PM
Security Audit — agent-trust-hub — qwen-image-2-pro