bx-image
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as documentation for the
bx-imagemodule, providing examples for BIF (Built-in Function), Fluent API, and Component-based image processing. - [EXTERNAL_DOWNLOADS]: The skill mentions installation commands like
install-bx-module bx-imageandbox install bx-image. These refer to the official BoxLang and CommandBox package management ecosystems, which are standard for the platform. - [DATA_EXPOSURE]: While the skill demonstrates reading from a URL (
ImageRead("https://example.com/image.png")), it is a benign example of typical image processing functionality and does not involve exfiltration of sensitive data. - [INDIRECT_PROMPT_INJECTION]: The skill describes an attack surface for processing images from user-supplied paths (
uploadPath) and URLs. However, it does not demonstrate any unsafe handling or execution of data contained within those images that would bypass agent safety boundaries. Standard sanitization of paths is recommended in production environments.
Audit Metadata