The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data that is subsequently passed to an external AI service (ElevenLabs).
Ingestion points: The --prompt command-line argument and JSON files provided via the --composition argument in scripts/generate_music.ts are ingestion points for untrusted data.
Boundary markers: There are no explicit delimiters or instructions provided to the downstream API to treat the input as untrusted data or to ignore embedded instructions.
Capability inventory: The skill utilizes network access to communicate with the ElevenLabs API and has file system write access to save the resulting audio files.
Sanitization: No sanitization, escaping, or validation of the text prompts is performed before they are interpolated into the API request body.
[COMMAND_EXECUTION]: The skill's primary interface is a command-line script (generate_music.ts) which requires the user to execute shell commands to generate music.
[EXTERNAL_DOWNLOADS]: The skill relies on external Node.js dependencies defined in scripts/package.json (including dotenv, ts-node, and typescript) which are downloaded from the NPM registry during setup.

music-generator