NYC

deep-research

Warn

Audited by Snyk on Feb 19, 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). This skill sends queries to the Gemini Deep Research agent (see SKILL.md and README stating it "searches the web and analyzes sources" and "reads and extracts relevant information" / "Web-only research"), so it clearly ingests untrusted public web content that the agent reads and uses to generate and drive research outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 03:58 PM