CrowdStrike data and OpenAI's admission confirm prompt injection as a dominant enterprise AI attack vector. 65% of ...

To prevent prompt injection attacks when working with untrusted sources, Google DeepMind researchers have proposed CaMeL, a defense layer around LLMs that blocks malicious inputs by extracting the ...

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

The controversy over vibe coding reached a new high this week after a developer added hidden instructions to his open source Java testing app to sabotage projects performed by AI coding agents. The ...

The huge data thefts at Heartland Payment Systems and other retailers resulted from SQL injection attacks and could finally push retailers to deal with Web application security flaws. This week’s ...

A novel class of attack techniques against modern Intel processors can allow threat actors to inject malicious data into applications via transient-execution attacks and steal sensitive data according ...

OpenAI has launched a new security feature called Lockdown Mode for ChatGPT users. The feature is designed to reduce the risk of prompt injection attacks and unauthorized data exposure by restricting ...

Microsoft assigned CVE-2026-21520, a CVSS 7.5 indirect prompt injection vulnerability, to Copilot Studio. Capsule Security discovered the flaw, coordinated disclosure with Microsoft, and the patch was ...