skills/ortus-boxlang/skills/bx-image/Gen Agent Trust Hub

bx-image

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents the 'bx-image' module, which is an official resource provided by the author 'ortus-boxlang'.
  • [COMMAND_EXECUTION]: Instructions include the use of 'box install' and 'install-bx-module' for package management, which are standard for the BoxLang ecosystem.
  • [EXTERNAL_DOWNLOADS]: The 'ImageRead' function is documented to support fetching images from remote URLs. This is an intended feature for image processing workflows.
  • [PROMPT_INJECTION]: Indirect surface: The skill includes functionality to process external data via 'ImageRead' which may contain untrusted metadata.
  • Ingestion points: 'ImageRead' accepts external URLs and file paths in SKILL.md.
  • Boundary markers: Absent; no specific instructions are provided to ignore data within image headers or metadata.
  • Capability inventory: Network read, file system read/write in SKILL.md.
  • Sanitization: Absent; the skill does not demonstrate validation of image content or metadata before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 02:44 PM