The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of user-provided text prompts and reference images to drive asset generation via tools like recommend and model_run.
Ingestion points: User-supplied prompt and referenceImages parameters (SKILL.md).
Boundary markers: The instructions do not define specific delimiters for separating user content from system instructions.
Capability inventory: The skill utilizes model_run for remote API execution and asset_download for file retrieval (SKILL.md).
Sanitization: Input content is processed by generative models which are expected to maintain their own safety boundaries.
[COMMAND_EXECUTION]: The skill provides guidance for the user to manually install sibling skills using the npx skills add scenario-labs/skills command, which is a standard procedure for expanding capabilities within the author's ecosystem.
[SAFE]: All identified model identifiers and tool patterns are consistent with the documented purpose of the skill and the author's verified infrastructure.

scenario-textures