scientific-slides

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/generate_slide_image.py to call its internal AI generation script and in scripts/validate_presentation.py to execute pdflatex. These are standard operations for the skill's purpose of orchestrating Python logic and compiling LaTeX documents.
  • [EXTERNAL_DOWNLOADS]: The scripts/generate_slide_image_ai.py file communicates with openrouter.ai to send prompts and receive generated images. OpenRouter is a well-known service for accessing AI models, and the connection is necessary for the core functionality of the skill.
  • [CREDENTIALS_UNSAFE]: The skill manages its required OPENROUTER_API_KEY through environment variables and .env files. This is a standard and recommended practice for secret management in developer tools; no hardcoded secrets or unsafe exposures were found.
  • [REMOTE_CODE_EXECUTION]: While the skill involves AI-generated content, the output is restricted to image files (.png, .jpg) which are then compiled into a PDF. There is no pattern of downloading and executing arbitrary remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:17 AM