Microsoft warns of AI recommendation poisoning where hidden prompts in “Summarize with AI” buttons manipulate chatbot memory and bias responses.

Wallarm released today The 2026 API ThreatStats Report, a data-driven analysis of API attack telemetry, published vulnerabilities, confirmed exploitation, and API-related breaches disclosed in 2025.

Threat actors now have the ability to exploit a new zero-day vulnerability in the Chrome browser, Google has advised IT ...

Here are three papers describing different side-channel attacks against LLMs. “Remote Timing Attacks on Efficient Language Model Inference“: Abstract: Scaling up language models has significantly ...

Adversa AI today announced the release of SecureClaw, an open-source, OWASP-aligned security platform consisting of plugin and behavioral security skill designed to secure OpenClaw AI agents.

In the news release, SecureClaw by Adversa AI Launches as the First OWASP-Aligned Open-Source Security Plugin and Skill for OpenClaw AI Agents, issued Feb. 16, 2026 by Adversa AI over PR Newswire, we ...

Leaked API keys are nothing new, but the scale of the problem in front-end code has been largely a mystery - until now. Intruder's research team built a new secrets detection method and scanned 5 ...

A fake CAPTCHA scam is tricking Windows users into running PowerShell commands that install StealC malware and steal passwords, crypto wallets, and more.