Inter-Agent Communication

Warn

Audited by Snyk on Feb 16, 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 performs discovery via directory.lookup and sends/receives messages to arbitrary agent endpoints (e.g., payment_agent_url/inbox and an agent marketplace/registry), meaning it ingests and interprets responses from untrusted third-party agents.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:45 AM