Meta’s AI support chatbot proved unusually helpful to hackers looking to steal and resell notable Instagram accounts—the ...

Meta has patched an AI chatbot vulnerability that allowed hackers to reset Instagram account credentials through prompt ...

A severe security flaw in Meta’s automated AI support assistant allowed hackers to hijack high-profile Instagram accounts via basic prompt injection. Attackers spoofed target locations via a VPN and ...

As South African businesses increasingly deploy AI agents across HR, finance and supply-chain operations, cybersecurity experts are warning that a new threat is emerging: prompt injection attacks that ...

SpartanX, the world’s only full-stack AI-powered autonomous red teaming platform, today announced the release of NodeX, its new Internal Attack Capability that extends SpartanX’s External Attack ...

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.

Why the first AI-orchestrated espionage campaign changes the agent security conversation Provided byProtegrity From the Gemini Calendar prompt-injection attack of 2026 to the September 2025 ...

A now corrected issue allowed researchers to circumvent Apple’s restrictions and force the on-device LLM to execute attacker-controlled actions. Here’s how they did it. Interestingly, they ...

MetaMask has indicated in an ecosystem report that the Bitcoin and cryptocurrency ecosystem in May 2026 faced escalating ...