gpt-image-markup-edit

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes JSON specification files (e.g., examples/nook.json) to generate image markups. The label and note fields within these JSON files are directly interpolated into the prompts presented to the agent and the downstream image model.
  • Ingestion points: Specification files passed to scripts/markup.py (e.g., via workspace files or generated content).
  • Boundary markers: Absent; instructions in SKILL.md direct the agent to use the output lines of the script verbatim in the image tool prompt.
  • Capability inventory: Access to curl for API interaction, python3 for image generation, and magick for diffing images.
  • Sanitization: No sanitization or escaping is performed on the label or note text before it is printed and subsequently used in prompts.
  • [COMMAND_EXECUTION]: The skill relies on several shell-based tools to perform its tasks.
  • Evidence: Uses python3 to run the scripts/markup.py image processing script, magick (ImageMagick) to verify image changes via magick compare, and curl to upload files to the varg.ai API.
  • [EXTERNAL_DOWNLOADS]: The skill references and interacts with external domains for image hosting and API services.
  • Evidence: Interacts with s3.varg.ai and mcp.varg.ai. These resources belong to the vendor (vargHQ) and are used for legitimate image storage and model invocation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:49 PM