gemini-deepresearch

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves deep research that queries public web search results and consumes user-provided local directories/attachments or outlines, but does not monitor or automatically ingest unauthenticated outsider-authored free text feeds (such as email, issues, or chat feeds) without prior selection.