building-ai-chat

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and displays user-provided, untrusted multi-modal content (e.g., the "Multi-Modal Support" section with ImageUpload and ImageMessage examples that handle user-uploaded images/files/voice for AI analysis), meaning the agent will ingest and interpret third-party user-generated content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:08 PM