brand-voice-extractor

Warn

Audited by Snyk on Feb 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md "Extract" mode explicitly requires ingesting 3–5 pieces of content (e.g., website copy, top-performing LinkedIn posts, emails) that are user-generated/public and the agent must read and codify them into a voice profile that will materially drive subsequent content-generation actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 08:46 AM