Security researchers have discovered 10 new indirect prompt injection (IPI) payloads targeting AI agents with malicious ...
Every secure API draws a line between code and data. HTTP separates headers from bodies. SQL has prepared statements. Even email distinguishes the envelope from the message. The Model Context Protocol ...
The discovery involves a vulnerable GitHub workflow, within the Windows-driver-samples repository. Tenable Research has ...
A design choice in the MCP SDKs allows remote code execution across the AI supply chain.
CVE-2026-5760 (CVSS 9.8) exposes SGLang via /v1/rerank endpoint, enabling RCE through malicious GGUF models, risking server ...
Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...
A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...
Yubico warns of a search path vulnerability in YubiKey Manager, libfido2 and python-fido2. Updates fix the bugs.
Code that might appear correct but actually misses edge cases or generates inaccurate results can trigger outages, faulty ...
Anthropic fixed a significant vulnerability in Claude Code's handling of memories, but experts caution that memory files will ...
As AI agents increasingly rely on third-party API routers, criminals are using this dependence to trick users and inject malicious code into their machines.