The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_schematic.py utilizes the subprocess module to execute a secondary internal script (generate_schematic_ai.py). The implementation is secure as it passes command arguments as a list and does not use shell=True, which effectively mitigates command injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill communicates with openrouter.ai to access generative AI models for creating and reviewing diagrams. OpenRouter is a well-known service, and the usage is consistent with the skill's stated purpose.
[CREDENTIALS_UNSAFE]: The skill requires an OpenRouter API key. The documentation and scripts correctly advise users to provide this via environment variables or local .env files, avoiding hardcoded secrets in the codebase.
[DATA_EXFILTRATION]: No malicious data exfiltration patterns were detected. The only data sent externally is the user-provided diagram description and the generated images for quality assessment by the designated AI models.

scientific-schematics