The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python's subprocess module to manage its internal script lifecycle. Specifically, scripts/generate_schematic.py executes scripts/generate_schematic_ai.py using a list-based command structure that prevents shell injection vulnerabilities. The skill also documents the use of common utilities like libreoffice and google-chrome for file conversion tasks.
[EXTERNAL_DOWNLOADS]: The skill performs legitimate network operations to openrouter.ai, a well-known AI platform, to facilitate image generation. This communication is required for the skill's primary functionality and does not involve untrusted code execution or unexpected data transfers.
[CREDENTIALS_UNSAFE]: The AI generation scripts handle API keys securely by retrieving them from environment variables or local .env files. No hardcoded credentials or sensitive secrets were found in the provided source code, adhering to standard security practices for secret management.
[DATA_EXFILTRATION]: Analysis confirmed that network activity is restricted to the intended AI service endpoint. There is no unauthorized access to sensitive system files (such as SSH keys or AWS credentials) and no evidence of data being sent to suspicious third-party domains.

pptx-posters