LodeHQ
AI news for people who shipFree, by email

Infosec · Thursday, 6 August 2026 · Issue 66 · 6 stories

Zero-Click AI Browser Hijack, Oracle SQLi to SYSTEM, KVM Guest Escape

Vulnerabilities & Exploits

Zero-Click ‘PleaseFix’ Attacks Let Hackers Hijack Claude, ChatGPT Atlas and Other AI Browsers

Researchers unveiled ‘PleaseFix’, a family of zero‑click flaws that let malicious emails, calendar invites or web pages silently commandeer AI‑enabled browsers like Claude in Chrome, Gemini, Perplexity Comet, ChatGPT Atlas and Copilot Edge. Attackers can steal credentials, make unauthorized purchases, or even gain full device control without any user interaction.

darkreading.com ↗6 min read at source

AI Recommendation Poisoning Lets ‘Summarize with AI’ Buttons Bias Future Answers

Microsoft researchers found that hidden prompts in ‘Summarize with AI’ buttons can silently write persistent instructions into an assistant’s memory, biasing later answers toward a vendor. Over 50 unique payloads from 31 firms across 14 sectors have been observed, affecting health, finance and security recommendations. The blog outlines the attack vector and Microsoft’s emerging mitigations.

microsoft.com ↗16 min read at source

Privacy, Policy & Governance

You’re caught up.

That was all 6 stories in the 6 August issue.