ai-image-generation
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: All functionality is managed through the
beltCLI tool. The skill uses theallowed-toolsfrontmatter field to restrict the agent's shell access exclusively tobelt *commands, preventing arbitrary command execution and enforcing the principle of least privilege. - [EXTERNAL_DOWNLOADS]: The skill directs users to documentation and installation instructions hosted on the official
inference.shdomain and its associated GitHub repository. These references are transparently provided for setup and do not involve automated or hidden downloads. - [SAFE]: No malicious patterns such as obfuscation, credential harvesting, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing an interface for AI image generation services.
Audit Metadata