Over 2,800 exposed Google API keys may allow unauthorized Gemini AI access, risking data leaks and massive API charges.

Anthropic fixed the flaws – but the AI-enabled attack surfaces remain Security vulnerabilities in Claude Code could have allowed attackers to remotely execute code on users' machines and steal API ...

Claude Code flaws allow remote code execution and API key theft via untrusted repositories; three bugs fixed across 2025–2026 ...

Researchers uncover wormable XMRig campaign using BYOVD exploit and LLM-built React2Shell attacks hitting 90+ hosts.

Researchers say threat actors used the sophisticated — and unfortunately named — toolkit to target high-value networks for ...

OpenAI launches EVMbench to test AI agents on smart contract security days after Claude Opus 4.6-assisted code triggered a $1.78M DeFi exploit.

A newly-uncovered malware targeting the Android operating system seems to exploit Google’s Gemini GenAI tool to help it maintain persistence.

OpenAI introduces EVMbench to measure AI crypto security. Benchmark evaluates detection, patching and exploit skills. OpenAI has launched a benchmarking system called EVMbench to evaluate how ...

Most API vulnerabilities are fast, remote, and easy to exploit. Attackers take full advantage of these attributes.

Truebit lost $26 million after a smart-contract overflow bug let an attacker mint tokens at near-zero cost, sending the TRU price down 99%. A $26 million exploit of the offline computation protocol ...

Windows doesn’t offer a single switch to disable Exploit Protection completely. You can only disable individual mitigations system-wide or per app. We strongly recommend turning it off only for ...

Crypto exchange SwissBorg said about 192,600 SOL ($41.5 million) was stolen from an external wallet used exclusively for its SOL Earn strategy on Monday. The exploit stemmed from a partner's ...