brave-search

Warn

Audited by Snyk on Mar 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: 1.00). The SKILL.md shows the agent using the Brave Search API (brave_web_search, brave_news_search, etc.) to retrieve results from public websites and explicitly instructs extracting URLs and "Use Code Buddy to fetch and summarize" those pages, so untrusted third‑party content is fetched and can influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 07:13 AM
Issues
1