ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the belt CLI from the inference-sh GitHub organization and recommends installing additional related skills via npx. These are documented as requirements for the skill's intended functionality.
  • [COMMAND_EXECUTION]: The skill utilizes the belt command to interact with image generation models. The execution environment is appropriately scoped using the allowed-tools frontmatter to restrict access to the belt binary.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and image URLs which are passed to the image generation platform. While this constitutes an input surface for potential indirect prompt injection (e.g., instructions embedded in prompts), the skill's current implementation for generating image assets does not present a feedback loop to the agent that would facilitate instruction execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 08:22 PM