The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes subprocess.run to interact with external system utilities ffmpeg and ffprobe. These operations are essential for the skill's primary functions, which include audio format conversion, metadata extraction, and merging multiple audio files. The implementation follows security best practices by passing arguments as lists rather than shell strings, which prevents common shell injection vulnerabilities.
[DYNAMIC_EXECUTION]: The check_environment.py script uses the __import__ function to programmatically verify that required dependencies (like the requests library) are installed on the system. This usage is restricted to environment validation and does not involve executing untrusted or dynamically generated code.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from segments.json files, which contain text to be converted into speech. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the text. However, the processing pipeline is limited to generating audio files via an external API and does not provide a path for these instructions to be executed as commands or influence the agent's logic, resulting in a low-risk profile.

mm-easy-voice