telekom

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

• Third-party content exposure detected (low risk: 0.10). The agent reads arbitrary web pages and search results from telekom.com via Unbrowse MCP tools, allowing ingestion of outsider-authored content upon active retrieval.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a remote third-party MCP server hosted at unbrowse.ai, which provides executable instructions and runtime tool definitions, constituting a common unofficial operational dependency.