skills/elevenlabs/skills/agents/Gen Agent Trust Hub

agents

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides users to install verified ElevenLabs packages including @elevenlabs/cli and @elevenlabs/elevenlabs-js via NPM and the elevenlabs package via Pip. It also references a widget integration script hosted on the well-known unpkg.com CDN.
  • [COMMAND_EXECUTION]: Provides administrative and deployment commands for the elevenlabs CLI tool to manage agent configurations.
  • [PROMPT_INJECTION]: The skill facilitates the creation of AI agents that process user-supplied input, creating an indirect prompt injection surface. This is addressed through documentation and implementation of platform-native safety guardrails.
  • [DATA_EXFILTRATION]: Documents 'Webhook Tools' that can be configured to send conversation data to developer-specified endpoints. This is a core architectural feature of the platform and is presented with instructions for secure authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:07 PM