Model Security Is the Wrong Frame – The Real Risk Is Workflow Security
Summary: Two Chrome extensions posing as AI helpers were caught stealing ChatGPT and DeepSeek chat data from over 900,000 users, and separately researchers showed prompt injections hidden in code repositories could trick IBM's AI coding assistant into running malware on a developer's machine. Neither attack broke the AI algorithms; both exploited the context around the model, and the article argues the workflow, not the model, is the real target.
What you should know: Over 900,000 users had AI chat data taken by extensions that never touched the model itself, which means the inputs, outputs, and integration points around your AI tools are the attack surface your legacy defenses were not built to watch.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026