brave-web-search
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill documentation.- [EXTERNAL_DOWNLOADS]: The skill interacts with the official Brave Search API and references ranking configurations hosted in Brave's official GitHub repository. These are well-known and expected sources for the intended functionality.- [DATA_EXFILTRATION]: The API supports optional location headers (latitude and longitude) to provide geographically relevant search results. This data is transmitted directly to the official search service as part of the documented feature set.- [PROMPT_INJECTION]: The skill ingests untrusted content from the public web via search result snippets. This creates an indirect prompt injection surface where third-party content could attempt to influence the agent's logic, a known risk inherent to all web search tools.
Audit Metadata