scientific-slides

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Credential management is handled securely by fetching the OPENROUTER_API_KEY from environment variables or a local .env file, adhering to standard development practices.\n- [COMMAND_EXECUTION]: The validate_presentation.py script uses subprocess.run to invoke pdflatex for checking the compilation of LaTeX Beamer templates. This is a functional requirement for the skill's purpose and is performed within the local environment.\n- [COMMAND_EXECUTION]: The generate_slide_image.py script acts as a wrapper, executing the internal generate_slide_image_ai.py script via subprocess.run. The command construction uses static script paths and user-provided prompts as arguments.\n- [EXTERNAL_DOWNLOADS]: The skill interacts with the OpenRouter API (openrouter.ai) to generate slide images. This is a recognized external service, and the data transmitted (slide descriptions and context images) is consistent with the skill's stated functionality.\n- [DATA_EXFILTRATION]: While the skill sends data to an external API, it is limited to user-provided slide content and requires an explicit API key, presenting no evidence of unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 10:21 AM