elevenlabs

Warn

Audited by Snyk on Oct 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The skill integrates with ElevenLabs via the Membrane CLI, allowing the agent to retrieve text-to-speech history, voice details, and user-generated content from ElevenLabs API endpoints.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an external CLI tool (@membranehq/cli) from npm during runtime setup, constituting an operational dependency with unverified community provenance.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 21, 2026, 03:16 PM
Issues
2