The Polish CERT warns of attacks on a command injection vulnerability in the Zimbra Collaboration Suite. An update is available.

Security leaders must adapt large language model controls such as input validation, output filtering and least-privilege access for artificial intelligence systems to prevent prompt injection attacks.

OpenAI’s GPT-5.6 prompt-injection tests show stronger direct defenses but higher agentic attack rates, raising new enterprise security concerns.

Although not the first of its kind, researchers’ POC attack against Microsoft’s M365 Copilot Enterprise underscores parameter-to-prompt (P2P) injections as a potentially broad threat. A recent ...

Security researchers have developed a new image-based prompt injection attack that can manipulate how multimodal AI systems interpret user instructions without modifying the original text prompt, ...

Japan's national vulnerability coordination body published its third consecutive advisory disclosing OS command injection flaws in Elecom's networking hardware today, flagging high-severity command ...

Auto Review’s AST analysis clears 82% of shell commands without an AI call, but the Shell Reviewer can still be reached by ...