The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides installation instructions that fetch official vendor components from trusted repositories.
Fetches a shell installer for the ElevenLabs CLI from the vendor's official GitHub repository (github.com/elevenlabs/cli).
References standard package managers to install official libraries for Python (elevenlabs) and Node.js (@elevenlabs/elevenlabs-js).
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for music generation, representing a standard vulnerability surface for prompt injection.
Ingestion points: The prompt and composition_plan fields in SKILL.md and references/api_reference.md are the primary entry points for user-provided instructions.
Boundary markers: No specific delimiters or warnings to ignore embedded instructions are included in the prompt examples.
Capability inventory: The skill examples demonstrate reading local files (video/audio for scoring/inpainting), writing audio to the file system, and making network requests to the ElevenLabs API.
Sanitization: Explicit sanitization is not detailed in the skill, as input validation and safety filtering are handled by the backend API service.
[COMMAND_EXECUTION]: The documentation includes examples of executing the elevenlabs CLI for music composition, which is consistent with the skill's purpose as a developer integration tool.

music