scientific-slides

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external commands via the subprocess module to perform legitimate tasks. This includes invoking helper scripts for AI generation and calling LaTeX compilers (like pdflatex) to build presentation PDFs from source templates.
  • Evidence includes calls in scripts/generate_schematic.py, scripts/generate_slide_image.py, and scripts/validate_presentation.py using secure list-based argument passing.
  • [EXTERNAL_DOWNLOADS]: The Python scripts generate_slide_image_ai.py and generate_schematic_ai.py communicate with the OpenRouter API (openrouter.ai) to generate and review slide images. This is a well-known service used for the primary purpose of the skill.
  • [DATA_EXPOSURE]: The skill requires an API key for its AI operations, which it retrieves from environment variables or a .env file. It sends user-provided prompts and attached image data to the AI service for processing, which is expected behavior for its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 05:26 AM
Security Audit — agent-trust-hub — scientific-slides