agent-router-setup

Warn

Audited by Snyk on Aug 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The required runtime hook assets/agent-router.mjs ingests outsider-authored free text from the Agent tool call (stdin fields tool_input.description + tool_input.prompt via taskText()), and it reads it before routing/denying.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 06:23 PM
Issues
1
Security Audit — snyk — agent-router-setup