PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...

Adversaries could plant a malicious repository that executes arbitrary code and steals cloud credentials, showcasing MCP risk ...

A vulnerability chain dubbed AutoJack in Microsoft's AutoGen Studio interface for prototyping AI agents could let attackers ...

Apache has fixed a critical security vulnerability in its open-source OFBiz (Open For Business) software, which could allow attackers to execute arbitrary code on vulnerable Linux and Windows servers.

It takes one file. A single chatflow import, the kind Flowise users share routinely, can give an attacker full command execution on the server running the application. The vulnerability, tracked as ...

Threat actors are exploiting vulnerabilities in Joomla and the LiteSpeed cPanel plugin for code execution and privilege ...

Thirteen critical vulnerabilities have been found in the vm2 JavaScript sandbox package that could allow an attacker’s code to escape the container and do nasty things to IT environments. As a result, ...

Researchers say that 'migrating to newer hardware remains the most effective mitigation' because the vulnerability resides in ...

AI frameworks, including Meta’s Llama, are prone to automatic Python deserialization by pickle that could lead to remote code execution. Meta’s large language model (LLM) framework, Llama, suffers a ...

F5 has patched multiple NGINX vulnerabilities, including critical flaws leading to unauthenticated, remote code execution.

Paradigm Shift’s usbliter8 exploit targets Apple A12 and A13 SecureROM via USB DFU mode, creating an unpatchable hardware ...