The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill serves as a guide for the agent to process user-supplied input, such as sound descriptions and text-to-speech scripts, which constitutes a data ingestion surface.
Ingestion points: The agent accepts physical event descriptions, music parameters (genre, instrumentation), and narration scripts from the user (SKILL.md).
Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" wrappers for user-provided scripts, relying instead on model fields like lyrics and text_to_speech parameters.
Capability inventory: The skill utilizes tools for listing base models, estimating forge prices, and polling for results (SKILL.md).
Sanitization: No specific sanitization or filtering logic is mentioned for the raw text provided for text-to-speech conversion.
[SAFE]: The skill references standard installation procedures within the author's own ecosystem.
The instruction to use npx skills add layerai/skills refers to the official repository of the skill author (layerai) for acquiring necessary sibling skills.

layer-audio