eu-ai-act-report-oliver-schmidt-prietz

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s Phase 1 “Input Collection” ingests the user/attacker-authored “Assessment Context” or free-form description (and later uses it for report content), which is directly exposed to prompt-injection via the user’s text.