skills/unbrowse-ai/sites/wikipedia/Gen Agent Trust Hub

wikipedia

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides integration with Wikipedia through a specialized MCP (Model Context Protocol) server hosted at unbrowse.ai. All external references and tools point to the vendor's own infrastructure (unbrowse-ai).
  • [EXTERNAL_DOWNLOADS]: The documentation mentions npx skills add and claude mcp add commands. These are standard procedures for adding agent skills or MCP servers and do not involve untrusted third-party code; they reference the vendor's official service.
  • [COMMAND_EXECUTION]: The skill provides instructions for adding the MCP server via CLI (e.g., claude mcp add). These are configuration commands for the user to set up the environment and are not executed automatically by the agent in a malicious way.
  • [CREDENTIALS_UNSAFE]: The documentation correctly advises users to store API keys in a secret manager and never commit them to configuration files, following security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:13 AM