{"uuid": "43f4ad90-be3c-4dae-817e-43705f9d39e7", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2025-6965", "type": "published-proof-of-concept", "source": "https://t.me/thehackernews/7161", "content": "\ud83d\uded1 Google\u2019s AI just stopped a cyberattack before it even began.\n\nAn LLM agent named Big Sleep discovered a critical SQLite flaw (CVE-2025-6965) that threat actors were likely about to exploit\u2014making it the first known case of an AI foiling a live exploit attempt.\n\nDetails on how it worked \u2192 https://thehackernews.com/2025/07/google-ai-big-sleep-stops-exploitation.html", "creation_timestamp": "2025-07-16T07:48:47.000000Z"}