The Agent Skills Directory

[CREDENTIALS_SAFE] (SAFE): The skill handles API keys via environment variables and .env files. No hardcoded secrets were detected; only placeholders for user configuration were found in the documentation.
[COMMAND_EXECUTION] (SAFE): The wrapper script scripts/generate_schematic.py uses subprocess.run() with a list of arguments to execute its internal AI logic script. This approach is safe and prevents shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS] (SAFE): The project identifies requests as its primary dependency. This is a well-known, trusted Python library. No suspicious third-party packages or unverified binaries are referenced.
[DATA_EXFILTRATION] (SAFE): Network operations are directed to openrouter.ai for the intended purpose of diagram generation. There is no evidence of the skill attempting to access sensitive local files (e.g., SSH keys, AWS credentials) or sending data to untrusted domains.
[PERSISTENCE] (SAFE): While the documentation suggests that users add the API key to their shell profile (~/.bashrc), the code itself does not perform any automated modifications to system files or startup scripts.

scientific-schematics