The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and image assets to generate video content, representing a standard interaction surface.
Ingestion points: User-provided data enters via the prompt and images parameters in SKILL.md for use with the model_run tool.
Boundary markers: No specific delimiters or "ignore instructions" markers are provided for user-supplied data.
Capability inventory: Tool access includes upload_asset, model_run, search, jobs_wait, and asset_display (defined in related skills).
Sanitization: No explicit input sanitization or filtering logic is described in the skill instructions.
[EXTERNAL_DOWNLOADS]: The documentation suggests the installation of additional tools from the vendor's own repository (scenario-labs/skills) via npx to support extended functionality.

scenario-vidu