ai-image-generation
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions utilize the
infshCLI tool for legitimate platform operations, including user authentication (infsh login), browsing available image models (infsh app list), and executing generation tasks (infsh app run). These commands are scoped within the provided examples to interact solely with the inference.sh ecosystem. - [EXTERNAL_DOWNLOADS]: The skill references external resources for environment setup, including installation instructions hosted on a public GitHub repository (
github.com/inference-sh/skills) and links to official documentation on theinference.shdomain. These references are used for user-directed configuration and do not involve automated execution of untrusted remote scripts. - [PROMPT_INJECTION]: The skill processes user-supplied strings as input for image generation prompts. It employs structured JSON objects to pass these prompts to the CLI tool, which serves as a standard method for separating user data from tool commands.
Audit Metadata