The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill's behavior aligns with its stated purpose of scientific diagram generation.
[COMMAND_EXECUTION]: The wrapper script scripts/generate_schematic.py uses subprocess.run() to call the internal AI generation logic. The implementation is secure as it uses a list of arguments and does not invoke the shell, preventing potential command injection.
[EXTERNAL_DOWNLOADS]: The skill makes legitimate network requests to openrouter.ai to interact with AI models. OpenRouter is a well-known service provider, and this external communication is essential for the skill's functionality.
[CREDENTIALS_UNSAFE]: The skill correctly handles the OPENROUTER_API_KEY using environment variables and optional .env file support. No actual secrets or API keys are hardcoded in the repository; documentation uses only placeholders.

scientific-schematics