The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes character briefs and interview answers provided by the user, which are then interpolated into prompts for image generation and identity management tools. Ingestion points: Character briefs, identity details (silhouette, proportions, palette), and signature details obtained via user interview as described in SKILL.md. Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the identity briefs. Capability inventory: The skill utilizes model_run for generation, collection_create and collection_add_assets for library management, and collection_remove_assets for asset manipulation. Sanitization: There are no explicit sanitization or validation steps mentioned for the user-supplied identity parameters before they are passed to tools.
[EXTERNAL_DOWNLOADS]: The skill contains instructions for the agent to recommend the installation of additional dependencies from the author's official repository. Evidence: The text suggests the user run npx skills add scenario-labs/skills to resolve missing sibling skills. Note: The target repository is owned by the skill author (scenario-labs) and constitutes a vendor resource.

scenario-identity-library