The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script at skills/shared/scripts/asr.py to transcribe video files.- [EXTERNAL_DOWNLOADS]: The transcription script fetches pre-trained AI models (faster-whisper) from external sources during its initial setup.- [INDIRECT_PROMPT_INJECTION]: The skill processes transcription data derived from user-provided video files, creating a potential surface for indirect prompt injection.
Ingestion points: The skill reads transcript.json containing the transcribed content of the video.
Boundary markers: No explicit delimiters or instructions are provided to the LLM to ignore potentially adversarial content within the transcript.
Capability inventory: The skill has permissions to execute local scripts and write files to the project's output directory.
Sanitization: No sanitization or verification of the transcript content is performed before processing.

video-chapters