Growth & Learning

Warn

Audited by Snyk on Feb 26, 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). This skill explicitly ingests untrusted, user-generated content — e.g., "YouTube Comments" and "Social Mentions" listed under Feedback Integration SKILL.md and "Gather comments from YouTube Studio or API" — and the agent is instructed to read/categorize those comments and update the lessons/knowledge base that drive recommendations and future actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 08:29 AM