ai-image-generation
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external installation instructions at
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdand provides links to theinference.shdocumentation. These resources are hosted on infrastructure associated with the skill vendor. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings (prompts) and external image URLs to perform image generation and editing tasks. This represents a potential attack surface where adversarial input could influence the behavior of the underlying AI models or the CLI tool.
- Ingestion points: User-supplied prompts and image URLs included in the JSON input for
belt app runcommands (e.g., inSKILL.md). - Boundary markers: The skill uses JSON formatting to structure the input arguments for the CLI, providing a basic level of data separation.
- Capability inventory: The skill utilizes the
Bashtool to executebeltCLI commands. - Sanitization: No explicit validation or escaping logic for user prompts or image metadata is described in the skill instructions.
Audit Metadata