The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references installation instructions and documentation from a GitHub repository associated with the inference-sh organization. This is routine for configuring external CLI dependencies.
[COMMAND_EXECUTION]: The skill uses the belt command-line interface to interact with the ElevenLabs API via the Bash tool. The scope is limited to the belt binary as defined in the allowed-tools frontmatter.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a sink for text data intended for speech synthesis, creating an ingestion surface for untrusted content.
Ingestion points: The text field within the JSON input passed to the belt app run command in SKILL.md examples.
Boundary markers: None explicitly defined in the provided usage examples.
Capability inventory: Executes shell commands via Bash(belt *) to perform the API calls.
Sanitization: No specific sanitization or filtering of the input text is documented, which is standard for text-to-speech utilities where the text is the intended payload.

elevenlabs-tts