The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified within the skill's code or documentation.
[EXTERNAL_DOWNLOADS]: The skill utilizes the google-genai and requests Python libraries to communicate with official API endpoints. These are standard packages from trusted and well-known providers.
[PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it processes user input for external video generation.
Ingestion points: The prompt command-line argument in scripts/generate_video.py is the primary entry point for untrusted data.
Boundary markers: There are no specific boundary markers or instructions to ignore embedded commands within the prompt logic.
Capability inventory: The skill makes network calls to api.openai.com and Google GenAI services and writes video files to the local file system.
Sanitization: Input is passed directly to the model clients without modification, which is standard behavior for generative tasks.

video-generator