The Agent Skills Directory

[SAFE]: The skill's primary file, SKILL.md, consists entirely of documentation, usage examples, and configuration metadata. It does not include any executable code, scripts, or automated triggers that could pose a security risk.
[EXTERNAL_DOWNLOADS]: The documentation provides links to the inference.sh CLI installation script on GitHub and references to other skills. These are well-known resources provided by the skill's vendor and are presented as informational links for the user, not as hidden or automated downloads.
[COMMAND_EXECUTION]: While the skill lists several bash command examples using the infsh CLI, these are clearly labeled as examples for the user to read and manually execute. The skill does not attempt to run these commands silently or automatically.
[DATA_EXFILTRATION]: No patterns of sensitive data access or exfiltration were detected. The skill's purpose is to facilitate text-to-speech generation, and its instructions are limited to that scope.
[PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override agent behavior, bypass safety filters, or extract system prompts.

elevenlabs-tts