The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and fetches guidelines and installation instructions from the official inference-sh GitHub repository.
[COMMAND_EXECUTION]: The skill uses the belt CLI to interact with the ElevenLabs music generation API and perform tasks like user authentication and app execution.
[INDIRECT_PROMPT_INJECTION]: The skill takes user-provided text prompts as input for music generation, which represents a standard surface for processing untrusted data.
Ingestion points: Untrusted data enters via the prompt parameter in the belt app run commands within SKILL.md examples.
Boundary markers: The instructions use JSON formatting (--input '{"prompt": "..."}') to structure inputs, providing clear delimiters between parameters.
Capability inventory: The skill uses the Bash tool to execute belt CLI commands and perform network-based API calls to the vendor's platform.
Sanitization: The skill relies on the belt CLI's internal handling of JSON-structured arguments to prevent command injection at the shell level.

elevenlabs-music