The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/transcribe.sh executes system commands to perform its tasks.
Evidence: The script invokes curl for API communication and node -e to execute an inline JavaScript block that processes the transcription data.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to external endpoints.
Evidence: It sends audio files and the OPENAI_API_KEY to the OpenAI Transcriptions API. The default destination is api.openai.com, which is a well-known service.
[PROMPT_INJECTION]: The skill acts as an ingestion point for external data that could contain malicious instructions (Indirect Prompt Injection surface).
Ingestion points: Audio files provided by the user are processed and converted to text via scripts/transcribe.sh.
Boundary markers: Absent; the script does not wrap the output transcription in delimiters or include instructions for the agent to ignore embedded content.
Capability inventory: The skill possesses file write capabilities and network access via the transcribe.sh script.
Sanitization: No sanitization or filtering is performed on the text generated from the audio input.

openai-whisper-api