brave-search

Warn

Audited by Snyk on Feb 16, 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). The skill's script scripts/brave-search.py calls the public Brave Search API (https://api.search.brave.com/res/v1/web/search) to fetch titles/descriptions/URLs from arbitrary web pages and returns/prints those results for the agent to read and interpret, exposing it to untrusted user-generated or public web content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:00 AM