review-us-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 ingests outsider-provided patent materials via “pasted claims”/uploaded DOCX/PDF/TXT/Markdown and office-action/amendment text in the required Intake/Workflow steps (e.g., extracting exact claim text and reviewing it), so the LLM reads free text submitted by the user/outsider without needing to select a specific item first.