The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/speak.ts executes system utilities including edge-tts, say, and afplay. The code uses Bun.spawn with argument arrays, which is a secure implementation that mitigates shell injection risks by avoiding direct shell execution of user-supplied strings.
[EXTERNAL_DOWNLOADS]: The skill relies on the edge-tts Python package. This is a well-known and standard tool for accessing Microsoft's neural text-to-speech services and is considered a safe dependency.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests and processes text from the agent that may originate from untrusted external sources. \n
Ingestion points: The text variable in scripts/speak.ts populated via command-line arguments. \n
Boundary markers: None. \n
Capability inventory: The script spawns subprocesses for speech synthesis and audio playback via Bun.spawn. \n
Sanitization: No validation or escaping is performed on the input text before it is passed to the TTS engines.

speak