HomeSecurityGoogle strengthens Chrome Agentic AI against Prompt Injection attacks

Google strengthens Chrome Agentic AI against Prompt Injection attacks

Google has announced new security updates for Chrome, aimed at protecting agentic AI from indirect prompt injection attacks. These attacks are a growing threat as malicious users try to exploit the capabilities of AI to perform unauthorized actions. To address this threat, Google has introduced a number of new security features.

See also: Google Gemini AI built into Opera One and Opera GX

agentic AI
Google strengthens Chrome Agentic AI against Prompt Injection attacks

One of the key additions is the 'User Alignment Critic', a feature that allows the AI ​​to assess whether the commands it receives are in line with the user's intentions and desires. This system acts as an additional layer of control, ensuring that the AI ​​does not perform actions that could be harmful or undesirable.

Additionally, Google has expanded its origin-isolation capabilities, which restrict AI access to data and functions not necessary to perform its tasks. This approach reduces the risk of exploiting vulnerabilities that could lead to unauthorized access to sensitive information.

Another important addition is user confirmations. Before the AI ​​performs certain actions, it will ask for confirmation from the user, ensuring that those actions are desired. This process adds an extra layer of security, reducing the possibility of malicious commands being executed.

See also: Google Gemini: Getting better at AI image detection

Google strengthens Chrome Agentic AI against Prompt Injection attacks
Google strengthens Chrome Agentic AI against Prompt Injection attacks

Google recognizes that indirect prompt injection attacks are a complex challenge as attackers continually evolve their methods. However, with these new features, the company aims to provide Chrome users with a safer browsing experience by strengthening AI protection against malicious attacks.

These updates are part of Google's ongoing effort to improve Chrome's security and protect users from new and emerging threats. The company encourages users to regularly update their software and stay up-to-date with the latest security developments.

Protecting agentic AI is critical as AI capabilities continue to expand and become embedded in more aspects of everyday life. Google is committed to keeping Chrome at the cutting edge of technology, providing a safe and reliable tool for its users.

See also: Google introduced the new, smarter Gemini 3 Pro

google gemini chatbot
Google strengthens Chrome Agentic AI against Prompt Injection attacks

With these new features, Google demonstrates its commitment to user security and protection, strengthening Chrome as one of the most secure browsers on the market.

Selecting the team

🔒 Protect your privacy with Proton VPN

Swiss VPN from the creators of Proton Mail — strict no-logs policy, strong encryption, and built-in NetShield that blocks ads, trackers, & malware.

  • ✔ No-logs, based in Switzerland (except 14-Eyes)
  • ✔ NetShield: blocks ads, trackers & malicious domains
  • ✔ Covers all devices — free version available
Try Proton VPN for free — 30-day money-back guarantee →

The link is an affiliate link — SecNews may receive a commission at no additional cost to you. It does not affect the independence of our article writing.

📧
Subscribe to the SecNews Newsletter

The most important Security & Technology news in your Inbox.

Absentee Mia
Absentee Miahttps://www.secnews.gr/politiki-syntaxis/
Member of the Editorial Team of SecNews. He writes about cybersecurity, online fraud, privacy and technology. All articles follow the SecNews Editorial Policy.

SEARCH

FOLLOW US

📧
Newsletter SecNews
The most important Security & Technology news in your inbox.

LIVE NEWS