The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs audio processing using FFmpeg through the subprocess.run() method. These calls are implemented securely using argument lists rather than shell strings, which effectively mitigates the risk of command injection from user-provided file paths or settings.
[EXTERNAL_DOWNLOADS]: The skill interacts with the MiniMax API (api.minimaxi.com and api-bj.minimaxi.com) to synthesize speech and download resulting audio files. These network operations are restricted to the vendor's legitimate service infrastructure and are essential for the skill's primary purpose.
[CREDENTIALS_UNSAFE]: Authentication is managed via the MINIMAX_VOICE_API_KEY environment variable. The skill does not contain hardcoded secrets, and its environment check script correctly identifies missing keys without exposing them.
[DATA_EXFILTRATION]: Analysis of the Python scripts confirms that network traffic is strictly limited to TTS synthesis requests and audio downloads. There is no evidence of sensitive local data (such as SSH keys or AWS credentials) being accessed or transmitted externally.
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on guiding the agent through a logical workflow for high-quality audio production. They include safety-conscious directions, such as requiring explicit user confirmation before deleting temporary files or finalizing plans.

mm-voice-maker