product-photography

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing the belt CLI tool (belt-sh/cli) and supplementary skills from the inference-sh repository. These references are consistent with the skill's primary function of providing a workflow for the inference.sh AI platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a template for generating image generation prompts based on user input. This creates an attack surface where a user might attempt to inject instructions into the generated shell commands. However, the scope is limited to creative image generation and the skill uses specific CLI arguments (--input) to pass data to the backend models.
  • [COMMAND_EXECUTION]: The skill uses the Bash(belt *) tool to execute image generation tasks. The commands are well-structured, using JSON inputs to interact with specific AI models (e.g., bytedance/seedream-4-5), which is standard practice for this type of integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:28 AM
Security Audit — agent-trust-hub — product-photography