The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external media files and provides the transcribed text to the agent for summarization. This creates a surface where spoken instructions in the audio could theoretically influence the agent's behavior during the summarization phase.
Ingestion points: The transcript file generated by the script is read by the agent.
Boundary markers: None are explicitly defined in the summarization process.
Capability inventory: The skill performs file writing and local script execution.
Sanitization: The transcription process records the spoken content as-is without filtering.
[EXTERNAL_DOWNLOADS]: The skill depends on the openai-whisper library, which downloads required model files from official repositories to the local machine during first use.
[COMMAND_EXECUTION]: The skill requires the agent to execute a local Python script (transcribe.py) to process media files, which is a standard part of its functionality.

media-transcriber