NYC

grpc-microservices

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: 0.70). The skill includes runnable chat and streaming examples (see EXAMPLES.md and SKILL.md — the ChatService/Chat and JoinRoom implementations) that accept and broadcast arbitrary ChatMessage.content from external clients (untrusted user-generated content), so an agent that reads or interprets those runtime messages would be exposed to potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:53 PM