youtube-thumbnail-design
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions for the
infshCLI hosted on the vendor's official GitHub repository (inference-sh/skills). - [COMMAND_EXECUTION]: Utilizes the
infshCLI tool to run image generation models and handle authentication. It also usesnpxto add related functional skills from the vendor's repository. - [PROMPT_INJECTION]: The skill defines a surface where text is passed as a prompt to an external image generation service.
- Ingestion points: The
promptfield within the JSON input for theinfshcommand inSKILL.md. - Boundary markers: The prompt is encapsulated within a JSON object passed as a command-line argument.
- Capability inventory: Execution of the
infshCLI via theBashtool. - Sanitization: The skill does not explicitly define sanitization logic for the input prompts, relying on the underlying platform or user for input validation.
Audit Metadata