kavel-image-studio
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for using the Kavel AI image transformation service. It provides legitimate direct links to the service's tools and structured prompt recipes.
- [DATA_EXFILTRATION]: All external URLs point to the official
kavel.aidomain, which is consistent with the skill's stated purpose. There are no attempts to access sensitive local files or credentials. - [REMOTE_CODE_EXECUTION]: The skill does not contain any code execution patterns or instructions to download external scripts. It references a
kavel-mcpserver as an optional tool, which is a standard pattern for agent tool integration. - [PROMPT_INJECTION]: The instructions are focused on guiding the agent to generate high-quality image prompts and do not contain bypass or override patterns.
Audit Metadata