gemini-deep-research

Warn

Audited by Snyk on Mar 1, 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.md explicitly states the Deep Research agent "searches the web systematically" and the script starts a Gemini "deep-research" agent interaction (scripts/deep_research.py) that instructs the agent to perform multi-source web research, meaning it will fetch and ingest untrusted public web content which can influence its decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:11 PM