The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external narration scripts (such as VOICEOVER-SCRIPT.md) to generate audio content. This constitutes an indirect prompt injection surface where text content from external files is ingested and processed by the agent.
Ingestion points: Text content is read from VOICEOVER-SCRIPT.md and processed via tools/voiceover.py or the /generate-voiceover command.
Boundary markers: There are no specific delimiters or boundary markers defined in the instructions to isolate the external script content.
Capability inventory: The skill uses network access to call the ElevenLabs API and file system access to write generated .mp3 files to the public/audio/ directory.
Sanitization: The instructions do not describe any sanitization or validation of the input script text before it is sent to the synthesis engine.
[COMMAND_EXECUTION]: The skill's documentation guides the user to execute local command-line tools, specifically python tools/voiceover.py and ffmpeg, for generating and processing audio assets. These commands are typical for a media generation workflow.

elevenlabs