The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the installation of the belt-sh/cli package via npx and links to external setup instructions hosted on a GitHub repository (inference-sh/skills).
[COMMAND_EXECUTION]: The skill relies on shell command execution using the belt CLI tool (authorized via Bash(belt *) in the frontmatter) to perform login operations and run the ElevenLabs TTS application.
[INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary user text to be converted into speech, which presents a surface for indirect prompt injection where malicious instructions could be embedded in the data being processed.
Ingestion points: The text parameter within the JSON input for the belt app run command in SKILL.md.
Boundary markers: None present; the input is directly interpolated into the command arguments.
Capability inventory: The skill has the capability to execute shell commands via the belt CLI.
Sanitization: No evidence of text sanitization or validation is provided in the instructions.

elevenlabs-tts