The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple commands using the listenhub CLI to manage voice cloning tasks. These executions are gated by strict interaction patterns, including the use of AskUserQuestion to ensure user authorization for credit-spending actions.- [EXTERNAL_DOWNLOADS]: The skill requires the listenhub binary, which is the primary tool for the vendor's service. This dependency is expected and documented as a prerequisite for the skill's functionality.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the ingestion of external audio files and the generation of preview URLs. However, the risk is mitigated by an explicit evidence chain: (1) Ingestion points: Audio files provided by the user in the workflow. (2) Boundary markers: The skill mandates a consent check and a manual preview step before finalization. (3) Capability inventory: CLI-based file reading and network uploads. (4) Sanitization: The skill follows shared CLI patterns and interaction guards to ensure data is handled within expected parameters.

voice-clone