gemini-deep-research

Warn

Audited by Snyk on Apr 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill automates a Chrome CDP session to navigate gemini.google.com and programmatically extract and act on the Gemini "plan" and full markdown report (see "Automation Flow" — "Extract plan text", "Auto-confirm 'Start research'", and "Extract report"), so untrusted third-party content from Gemini is read and can drive subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 4, 2026, 09:52 AM
Issues
1