seo-image-gen

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/cost_tracker.py, scripts/presets.py) to log generation costs and manage brand configuration files stored in the user's home directory (~/.banana/).
  • [COMMAND_EXECUTION]: Includes documentation and automated examples for image post-processing using magick (ImageMagick) and ffmpeg for tasks such as WebP conversion, resizing, and background removal.
  • [EXTERNAL_DOWNLOADS]: References the installation of the banana extension and the @ycse/nanobanana-mcp server from public repositories. These dependencies are required for the skill's primary purpose of image generation.
  • [PROMPT_INJECTION]: The skill uses user-supplied descriptions to dynamically construct a 'Reasoning Brief' for the image generation model. This represents an ingestion surface for indirect prompt injection where a malicious description could attempt to influence model behavior, though the impact is limited to the generation of the specific image.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:11 PM