brainstorm-with-file

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs external web searches and ingests results via web.run (see "Phase 2.3b: External Research" and Phase 3 "外部研究"), writing findings to research.json and merging them into perspectives/synthesis, so untrusted public web content can be read and materially influence decisions.