The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or associated scripts.\n- [COMMAND_EXECUTION]: The skill uses uv run to execute a local script for its core functionality. This is the intended operation and does not present an arbitrary command execution risk.\n- [EXTERNAL_DOWNLOADS]: Dependencies are limited to official and widely-used Python packages (google-genai, pillow). No remote scripts are fetched or executed.\n- [CREDENTIALS_UNSAFE]: The skill securely handles API keys by checking the GEMINI_API_KEY environment variable or an optional command-line argument, rather than hardcoding credentials.

nano-banana-pro