whatsapp-skill

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 skill directly fetches and returns user-generated WhatsApp content (e.g., via client.getChats(), chat.fetchMessages(), and client.searchMessages() in whatsapp_skill.js and the SKILL.md "Reading Chats & Messages" / "Search messages" workflow), so untrusted third-party messages could be read and materially influence the agent's decisions or subsequent messaging actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 03:20 PM