scientific-slides

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The validate_presentation.py script uses subprocess.run to execute the pdflatex command for compiling LaTeX documents. Additionally, generate_slide_image.py executes an internal helper script (generate_slide_image_ai.py). These operations are benign and essential for the skill's presentation-building workflow.
  • [EXTERNAL_DOWNLOADS]: The generate_slide_image_ai.py script communicates with the OpenRouter API (openrouter.ai) to generate slide content. This is a well-known service, and the network connection is a core requirement for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface that passes user-provided prompts to an external AI model. While this constitutes an attack surface for indirect prompt injection, the risk is standard for LLM-based applications and is managed by the upstream AI provider's safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 12:15 PM