singtel

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

• Third-party content exposure detected (low risk: 0.10). The agent reads product plans and pages from shop.singtel.com via the Unbrowse MCP, which fetches commercial website content that can contain arbitrary text published by outsiders.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server at https://unbrowse.ai/mcp/singtel.com which provides executable tool definitions and runtime behavior for the agent, constituting an unofficial third-party operational dependency.