javascript-sdk
Warn
Audited by Snyk on Feb 17, 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 includes explicit web-search and browsing capabilities (e.g., the RAG Pattern's search tool "tavily/search-assistant@latest", internalTools().webSearch(true), and "Working with URLs" / browser-automation examples) which cause the agent to fetch and ingest public/untrusted web content and arbitrary URLs that it will read and interpret.
Audit Metadata