web-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The web-search skill performs multi-engine web searches via scripts that ingest external search results and web page snippets from various third-party search APIs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx -y mcp-remote https://mcp.tavily.com/mcp to fetch and execute remote content during runtime authentication flow, introducing an unverifiable runtime external dependency under weak or unknown provenance.