Skills
Navigate
skills/sideshowroberto/vfx-agent-toolkit/magnific-image-gen/Gen Agent Trust Hub

magnific-image-gen

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill includes technical instructions for the agent to execute Python code snippets for calculating image dimensions and performing WebP to JPEG conversions using the Pillow library.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing untrusted external data by allowing the agent to fetch images from user-supplied URLs through the creations_upload_image tool.
  • Ingestion points: The url parameter in the creations_upload_image tool and the prompt parameter in images_generate (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the processed data.
  • Capability inventory: The skill has network access via dedicated tools and includes instructions for file writing and image processing using Python scripts (SKILL.md).
  • Sanitization: There are no instructions for sanitizing or validating the content of the external images or prompts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:18 AM