The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the user to install missing functional dependencies from the author's own repository using the npx skills add scenario-labs/skills command. This is a standard management procedure within the vendor's ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and media assets, which constitutes a potential attack surface for indirect instructions.
Ingestion points: Untrusted data enters the context via user-supplied scripts and uploaded photos or videos used for generation (Steps 3, 4, and 6).
Boundary markers: The skill recommends using quotes to delimit dialogue in prompts (Route table).
Capability inventory: The skill uses model_run to execute video/audio generation, upload_asset for file handling, and collection_add_assets for asset management.
Sanitization: The instructions mandate that the agent must confirm the final wording of the script with the user before generation and strictly forbids the creation of fabricated claims or testimonials.

scenario-ugc