Skills
Navigate
skills/kyh/vibedgames/elevenlabs/Gen Agent Trust Hub

elevenlabs

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The implementation patterns in references/api-patterns.md utilize the official @elevenlabs/elevenlabs-js library to interface with ElevenLabs services.
  • [PROMPT_INJECTION]: The skill describes a method for processing external text through an audio synthesis pipeline, which introduces an indirect prompt injection surface.
  • Ingestion points: Untrusted text enters the workflow via the text parameter in the synthesize function located in references/api-patterns.md.
  • Boundary markers: The provided implementation examples do not include delimiters or instructions to help the model distinguish between data and potential commands within the input string.
  • Capability inventory: The skill uses the elevenlabs.textToSpeech.convert function in references/api-patterns.md to transmit data to an external API.
  • Sanitization: No input validation or sanitization mechanisms are present in the code snippets provided.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 09:56 PM