The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-supplied text prompts to generate music, which creates a surface for indirect prompt injection attacks.\n
Ingestion points: The prompt parameter in the music.compose, music.composition_plan.create, and music.compose_detailed methods across SKILL.md and references/api_reference.md serves as the entry point for untrusted data.\n
Boundary markers: No explicit delimiters or instructions to the model to ignore embedded commands are included in the provided code snippets.\n
Capability inventory: The skill facilitates network communication with api.elevenlabs.io and file system operations to write audio files (e.g., output.mp3).\n
Sanitization: The provided examples do not demonstrate sanitization or validation of the input prompt strings before they are sent to the API.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install official ElevenLabs client libraries from standard package registries.\n
Evidence: references/installation.md specifies the installation of the elevenlabs Python package and the @elevenlabs/elevenlabs-js Node.js package.

music