gemini-deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly states the Deep Research agent "searches the web systematically" and scripts/deep_research.py sends queries to Gemini's Deep Research Agent which ingests and synthesizes open web content into reports, meaning untrusted third‑party webpages/user‑generated content can influence model outputs and behavior.