The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The installation guide in references/installation.md includes a method for installing the ElevenLabs CLI by fetching a shell script from the vendor's official GitHub repository and piping it to the shell (curl ... | sh). This represents a standard installation procedure for the vendor's own command-line tools.
[COMMAND_EXECUTION]: In references/streaming.md, the skill demonstrates real-time audio playback using the subprocess module to call the local ffplay utility. The script pipes generated audio data directly to the player's standard input.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of official libraries and tools, including the elevenlabs Python package, @elevenlabs/elevenlabs-js Node.js package, and ElevenLabs CLI via Homebrew, Scoop, and NPM, all sourced from the vendor's official registries and repositories.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and synthesize arbitrary text input into speech, which introduces a surface for indirect prompt injection.
Ingestion points: The text parameter in the convert and stream methods across Python and JavaScript examples.
Boundary markers: Examples do not explicitly show the use of boundary delimiters or specific safety instructions for the input text.
Capability inventory: The skill performs network API calls to ElevenLabs services and writes audio data to the local file system.
Sanitization: No explicit sanitization or filtering of the input text is described before synthesis.

text-to-speech