google-workspace
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the runtime browser-extraction steps (e.g., Gmail “get_page_text” after opening an email thread, and Drive/Sheets “read_page/get_page_text” after navigating to user-selected files/pages), where the extracted prose originates from other people’s emails/files or shared documents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata