NYC

agent-tools

Warn

Audited by Snyk on Feb 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly exposes the agent to open web/untrusted third‑party content by allowing execution of web-search apps (e.g., tavily/search-assistant, Exa Search) shown in the Quick Examples and "What's Available", so the agent would fetch and read public search results as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 10:11 AM