The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided text prompts and images for video generation, which is a standard surface for indirect prompt injection. 1. Ingestion points: Text prompt and image assets in model_run calls within SKILL.md. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present. 3. Capability inventory: Access to upload_asset and model_run tools for content generation. 4. Sanitization: No sanitization or validation of input data is described.
[COMMAND_EXECUTION]: The skill instructs the user to install additional components using npx skills add scenario-labs/skills, referencing the official repository of the author.

scenario-vidu