@davidbombal: Copilot Told Researchers How to Hack It Can AI tell you how to hack itself? Researchers kept questioning Microsoft Copilot until it revealed a clue that helped them uncover CoSnitch (CVE-2026-24301). A specially crafted link could automatically run an attacker’s prompt inside a signed-in Copilot Personal session. Researchers demonstrated data theft from connected services and memory poisoning that could influence future answers. Microsoft patched the issue on August 18, 2026. Varonis reported no evidence of exploitation in the wild at disclosure. Source: https://www.varonis.com/blog/cosnitch #ai #microsoftcopilotai #cybersecurity

Mike_Litoris :

Copilot told me how to hack my ps5

motow81 :

use proper hardware

ChatGPT :

Some guy from Poland gave a copilot access to his server for a "better sys admin administation" [Łzy radości]

Sir. Coto :

Bider1243 :

very intrested

EMMANATION🥹 :

jailbreak😁

Vittorio Zamparella :

just yesterday I built a skill with Claude so that a script can pilot Claude. This way Claude can shutdown itself, modify itself from outside and restart working seamlessly.

. :

❤️❤️❤️

sami.garbouj9 :

😳😳😳