Google hardens Chrome's agentic AI features against indirect prompt injection
Google announced defensive measures to harden Chrome's agentic AI capabilities against indirect prompt injection attacks. The news is dated 8 December 2025.
Who is affected and how
- security leader
- Agents built into the browser create a new attack surface that needs to be governed.
- developer
- Protection against indirect prompt injection is a basic requirement when designing agents that run in the browser.
Sources
- Google Fortifies Chrome Agentic AI Against Indirect Prompt Injection Attacks - SecurityWeeksecurityweek.com · Dec 8, 2025
- Hacking Google Gemini Enterprise with an Indirect Prompt Injection | Nomanoma.security · Dec 8, 2025
- Google Adds Multi-Layer Security to Chrome Against AI Prompt Injection Attacks on Geminih2s media · Dec 9, 2025
- UK NCSC Raises Alarms Over Prompt Injection Attacks - Infosecurity Magazineinfosecurity-magazine.com · Dec 9, 2025
- BreachWatch – Hacking Gemini prompt injection in Google Workspace | Perimeter.netperimeter.net · Dec 10, 2025
- Rising AI Prompt Injection Attacks Pose New Security Riskspetri.com · Dec 10, 2025
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article. News monitoring and analysis, not security advice. Attributions belong to those who made them.
What do you make of this piece?
The split shows after 20 votes.
Why? Your answer is not shown publicly; it helps the editors.