The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt CLI tool and references configuration guidelines hosted on the inference-sh GitHub repository. These resources are part of the platform's official tooling and documentation.
[COMMAND_EXECUTION]: The skill utilizes the belt command-line utility to interact with the ElevenLabs API, handle user authentication, and manage media processing workflows. Execution is restricted to the belt namespace via the platform's tool configuration.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to generate synthesized dialogue. This represents an attack surface where maliciously crafted text could attempt to influence the agent or the speech synthesis engine.
Ingestion points: Text fields within the JSON input for belt app run commands in SKILL.md.
Boundary markers: Data is structured within JSON objects using defined keys (segments, text, voice).
Capability inventory: The skill can execute shell commands through the belt tool and merge media files.
Sanitization: No explicit sanitization or filtering of the input text is described within the skill's instructions.

elevenlabs-dialogue