ai-einsatz-transparenz-datenschutz

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to search external legal databases like gesetze-im-internet.de, dejure.org, and openJur to verify norms, which involves fetching arbitrary web pages and search results rather than monitoring an outsider-submission queue.