The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script scripts/generate_schematic.py functions as a wrapper that calls a secondary Python script (generate_schematic_ai.py) using subprocess.run. It uses an argument list format which prevents shell injection and restricts execution to a specific local file path.
[EXTERNAL_DOWNLOADS] (SAFE): The skill requires the requests library and interacts with the legitimate openrouter.ai API. It does not perform any unverified remote code execution or download scripts from untrusted sources.
[CREDENTIALS_UNSAFE] (SAFE): The documentation and code correctly prioritize the use of environment variables (OPENROUTER_API_KEY) for authentication. No hardcoded credentials or secrets were found in the provided files.
[DATA_EXFILTRATION] (SAFE): Network operations are limited to the intended API provider for diagram generation. No patterns suggesting the exfiltration of sensitive local files or environment data were observed.

scientific-schematics