brand-voice

Warn

Audited by Snyk on Feb 27, 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 Mode 1 "Collect Samples" step explicitly asks the agent to "Paste the text or share files" including social media posts and website or blog copy, so the skill ingests untrusted/user-generated third-party content and will analyze it in ways that can influence downstream tool use and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 01:00 AM