The Agent Skills Directory

[COMMAND_EXECUTION]: The skill orchestrates audio processing by executing several Python scripts via the shell. These scripts are located within the ${CLAUDE_PLUGIN_ROOT} directory and include:
voice-generation/scripts/gemini_tts.py for text-to-speech.
music-generation/scripts/lyria.py for background music generation.
media-utils/scripts/audio_mix.py and audio_concat.py for audio assembly.
[EXTERNAL_DOWNLOADS]: The skill recommends the installation of ffmpeg using the Homebrew package manager (brew install ffmpeg). FFmpeg is a standard, well-known utility for audio and video processing.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect injection as it ingests untrusted data that flows into executable capabilities:
Ingestion points: User responses captured via the AskUserQuestion tool and contents of external text files (e.g., chapter1.txt) provided by the user.
Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings for the interpolated content.
Capability inventory: The skill uses python3 to execute scripts that take the user-provided text as command-line arguments (e.g., --text "...").
Sanitization: There is no evidence of escaping or sanitizing the user input before it is interpolated into shell command templates, creating a risk of command injection if the underlying agent platform does not provide automated protection.

audio-producer-agent