Keywords: Vulnerability


One in four French municipalities exposed to climate change risks and rising insurance costs

A growing share of French municipalities is becoming financially and structurally vulnerable to the impacts of climate change, with one in four communes now exposed to heightened risk and rising insurance costs, according to a new analysis by advocacy groups Reclaim Finance and Data For Good. The findings......

New Windows Defender zero-day enables system privileges escalation

A new security flaw has emerged in Microsoft Defender shortly after the release of a major Patch Tuesday update cycle. The vulnerability allows attackers to gain SYSTEM-level privileges on fully updated Windows 10 and Windows 11 machines. The issue stems from a race condition inside Microsoft Defender,......

European Central Bank warns banks on AI cyber threats

The European Central Bank will send a formal letter to all banks under its supervision, instructing them to strengthen defenses against cyberattacks driven by advanced artificial intelligence models. The move reflects growing concern within the institution about the speed and scale at which AI tools......

AI agent leaks passwords after simple social engineering trick in live experiment

A high-profile live experiment, a malware campaign hidden inside a fake plugin, and a new open-source scanning tool have converged this week to expose the depth of security vulnerabilities facing autonomous AI agent systems, with findings that carry serious implications for how such tools are deployed......

Microsoft AI agent security toolkit flaw exposes missing authentication checks

Microsoft faces scrutiny after a security analysis found that authentication checks in its open source AI agent governance toolkit are not executed in production code. The toolkit, released on April 3, was designed to provide runtime safeguards for autonomous AI agents and address risks outlined by OWASP......

Lovable denies breach after api flaw exposed user project data

Lovable is facing scrutiny after a security researcher revealed that a simple API vulnerability allowed unauthorized access to sensitive data across thousands of user projects. The company has denied that a data breach occurred, even as details of the flaw raised concerns about access controls and platform......

EU probes Anthropic over cybersecurity risks tied to mythos ai model

European regulators have stepped up scrutiny of artificial intelligence risks after the release of Anthropic’s Claude Mythos Preview, with authorities seeking clarity on its potential to expose critical vulnerabilities in digital infrastructure. The European Commission confirmed it has opened direct......

Anthropic AI protocol flaw exposes thousands of servers to attacks

A critical vulnerability in an artificial intelligence protocol developed by Anthropic could expose more than 200,000 instances and thousands of publicly accessible servers to cyberattacks, according to findings from security firm OX Security. The flaw affects the Model Context Protocol, an open standard......

Researchers hijack ai agents via github prompt injection attacks

Security researchers have demonstrated how artificial intelligence agents from Anthropic, Google and Microsoft can be compromised through prompt injection attacks hidden in GitHub workflows. The technique allowed attackers to extract API keys, GitHub tokens and other sensitive data without direct system......