scientific-schematics

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/generate_schematic.py serves as a wrapper that invokes the core AI generation logic located in scripts/generate_schematic_ai.py via a subprocess call.
  • Evidence: The wrapper script builds a command list containing the system's Python executable and the path to the internal AI script, executing it with subprocess.run() to manage the generation workflow.
  • [EXTERNAL_DOWNLOADS]: The skill connects to the OpenRouter API to access image generation and vision-language models.
  • Evidence: The script scripts/generate_schematic_ai.py utilizes the requests library to send POST requests to https://openrouter.ai/api/v1/chat/completions for diagram creation and quality assessment.
  • [DATA_EXFILTRATION]: User-provided diagram descriptions and the required OpenRouter API key are transmitted to an external service endpoint for processing.
  • Evidence: To function as intended, the skill sends the diagram prompt and the user's API token in the request headers and body to openrouter.ai. This is legitimate behavior consistent with the skill's primary purpose of AI-driven content generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 08:28 AM