dsv-erstgespraech-vorfallmeldung

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves checking legal databases like openJur and dejure.org live, but does not monitor an incoming unauthenticated outsider submission channel.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs live checking via external databases (gesetze-im-internet.de, dejure.org, openJur) without verifying their runtime content or provenance, triggering an unverified third-party dependency.