brave-search
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: 0.90). This skill queries the Brave Search API (e.g., https://api.search.brave.com/res/v1/web/search and the images/videos/news endpoints) and returns .web.results / .results fields (titles, URLs, descriptions) derived from public websites, news, and user-generated content that the agent is expected to read and interpret, exposing it to untrusted third‑party content.
Audit Metadata