web-search-brave

Warn

Audited by Snyk on Feb 24, 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 explicitly queries the Brave Search API (api.search.brave.com) in scripts/search.ts and SKILL.md to fetch web results, descriptions, and extra_snippets from arbitrary public websites, so untrusted third‑party content is ingested and presented for the agent to read and act on.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 02:40 AM