ultramsg

Warn

Audited by Snyk on Mar 28, 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 explicitly shows actions and proxy requests that fetch WhatsApp data via UltraMsg through Membrane (e.g., "List Messages", "List Chats", "List Groups" and the "membrane request" proxy), meaning the agent will ingest user-generated, third-party message content that could contain instructions influencing its subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 08:24 PM
Issues
1