ndr-de

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and reads pages on ndr.de via search and read tools, making outsider-authored content from the website accessible only through active search or URL fetching.

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 (unbrowse.ai) which acts as an operational runtime dependency providing tools and behavior-governing instructions, placing it in the common/reputable unofficial tier.