deepthink
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Step 3 の「Deep Research / Bulk Search」トリガーで
gemini.deep_researchやgrok.bulk_web_searchが実行され、外部Webページ等の“取得した自由テキスト”が LLM コンテキストに投入され得る(public web content fetched at runtime → LLM context)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata