patent-reviewer

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly ingests public third-party content (e.g., via search_patents_bigquery, search_patents_by_cpc_bigquery, the USPTO API and MPEP searches) and instructs the agent to read and integrate prior-art and USPTO/MPEP materials into drafting and decision workflows (see "Prior Art Integration" and the /create-patent and /full-review workflows), so external documents can materially influence tool actions and outputs.