The Agent Skills Directory

[SAFE]: The skill primarily serves as documentation for using the infsh CLI to access sound generation services. All commands and URLs are associated with the vendor's official domains and repositories.
[COMMAND_EXECUTION]: The skill uses the infsh tool to execute applications on the vendor's platform. These operations are within the scope defined in the allowed-tools configuration.
[EXTERNAL_DOWNLOADS]: The documentation links to installation instructions hosted on the vendor's GitHub repository (inference-sh/skills). This is a legitimate reference for setting up the required CLI environment.
[PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes user-supplied text descriptions to generate audio.
Ingestion points: The text parameter in the infsh app run command within SKILL.md.
Boundary markers: None present in the provided examples.
Capability inventory: Subprocess execution via the infsh CLI tool.
Sanitization: No explicit sanitization or input validation is described in the markdown documentation.

elevenlabs-sound-effects