deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill automates Gemini's "Deep Research" on https://gemini.google.com/app (see SKILL.md and scripts/deep-research.ts) which starts a research run that browses and ingests open-web third‑party content and the workflow explicitly waits for/uses those results, so untrusted web content can influence subsequent outputs.