review-ep-patent-claims-ip

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

• Third-party content exposure detected (medium risk: 0.30). The skill primarily ingests user-uploaded patent application/claim text and extracts claims/description/drawings content for its runtime review (Step 1 input handling), meaning outsider-authored free text can directly enter the LLM context without any prior selection from an external feed/queue.