airbnb

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

• Third-party content exposure detected (low risk: 0.10). The agent searches Airbnb listings via Unbrowse, meaning it retrieves arbitrary public property listings and descriptions chosen by search results, which constitutes low-risk outsider-authored content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect an external third-party MCP server from unbrowse.ai via HTTP transport, relying on it for operational tool execution and behavior configuration, which constitutes an unofficial third-party operational dependency.