The indirect prompt injection vulnerability allows an attacker to weaponize Google invites to circumvent privacy controls and ...

F5's Guardrails blocks prompts that attempt jailbreaks or injection attacks, and its AI Red Team automates vulnerability ...

Anthropic has launched Cowork with a known data exfiltration vulnerability that researchers reported in October 2025 but ...

The latest update from Microsoft deals with 112 flaws, including eight the company rated critical — and three zero-day ...

A vulnerability in the AIOSEO plugin affecting up to 3 million installations adds to the six vulnerabilities found in 2025.

Fortinet released updates for FortiOS and other products on Wednesday night. They fix, in some cases critical, ...

The first round of SAP patches for 2026 resolves 19 vulnerabilities, including critical SQL injection, RCE, and code ...

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...

Popular AI interface was plagued by an 8/10 bug, but a fix is now available.

Microsoft has pushed back against claims that multiple prompt injection and sandbox-related issues raised by a security engineer in its Copilot AI assistant constitute security vulnerabilities. The ...

A new report out today from artificial intelligence security startup Cyata Security Ltd. details a recently uncovered critical vulnerability on langchain-core, the foundational library behind ...

Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections, a type of attack that manipulates AI agents to follow malicious instructions often ...