The Agent Skills Directory

[SAFE]: The skill is a standard integration for the ElevenLabs text-to-speech API. All commands and instructions are aligned with the stated purpose of generating audio from text.
[EXTERNAL_DOWNLOADS]: The skill references the 'belt' CLI tool and provides installation instructions from the inference-sh/skills GitHub repository. This is the expected behavior for using this specific service provider.
[INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it ingests untrusted text data for processing.
Ingestion points: The --input JSON object within the belt app run commands in SKILL.md accepts arbitrary strings.
Boundary markers: None are present to delimit user input from instructions within the text-to-speech parameters.
Capability inventory: The skill is restricted to using the belt CLI tool via the Bash tool.
Sanitization: No explicit sanitization of the input text is described. However, as this is a text-to-speech utility, the risk of instruction following from the synthesized text is considered negligible.

elevenlabs-tts