The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_schematic.py uses subprocess.run to coordinate execution with scripts/generate_schematic_ai.py. This implementation is secure as it avoids using a shell (shell=True is not used), preventing command injection vulnerabilities even though it processes user-provided prompts as arguments.
[EXTERNAL_DOWNLOADS]: The skill communicates with the OpenRouter API (openrouter.ai) to generate and review images. This is a well-known service, and the communication is necessary for the skill's primary function. It also relies on the standard requests library for these operations.
[CREDENTIALS_UNSAFE]: The skill correctly manages sensitive data by instructing users to use environment variables (OPENROUTER_API_KEY) or .env files for their API keys, which is a standard security best practice to avoid hardcoding secrets.

scientific-schematics