The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts to generate music. This constitutes a surface for indirect prompt injection, as malicious instructions could be embedded in the prompt strings. However, the risk is minimal given the output is audio media.
Ingestion points: The prompt parameter in JSON inputs used with the belt command in SKILL.md.
Boundary markers: Data is structured within JSON objects, which provides clear separation between instructions and content.
Capability inventory: The skill utilizes the Bash tool to execute CLI commands for music generation and media merging.
Sanitization: Prompt sanitization is handled by the upstream inference provider.
[EXTERNAL_DOWNLOADS]: The skill references the belt CLI and auxiliary skills from the belt-sh and inference-sh GitHub organizations. These are official sources for the infrastructure described in the skill.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute belt CLI commands for logging in, running AI applications, and merging media. These operations are essential to the skill's purpose and are constrained by the allowed-tools configuration.

elevenlabs-music