A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw

Let op: Dit artikel is automatisch opgehaald uit een externe bron en nog niet vertaald of bewerkt. Publicatie vereist handmatige review.

Originele bron: The Hacker News

---

Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself. The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA’s Product Security Incident

Bron: The Hacker News — Lees het volledige artikel

Gerelateerde artikelen

AnalyseNewly SLEEPWALKER Backdoor Waits for One Crafted Packet, Then Runs Its Own BytecodeAn independent malware researcher has documented a previously unreported Windows backdoor, dubbed SLEEPWALKER, that stays inert in memory until a specifically crafted network packe...26 aug 2026AnalyseE4del and PINHOLE RATs Turn FTP Banners Into Dead Drops for Malware CommandsCybersecurity researchers are calling attention to a new campaign that employs FTP banners as dead drop resolvers (DDRs) to deliver two previously unreported remote access trojans...25 aug 2026AnalyseOperation QUICSILVER Targets Myanmar Government and IT with QUICAgent BackdoorCybersecurity researchers have flagged a cyber espionage campaign targeting Myanmar that uses graduation ceremony invitation lures to deliver a Go backdoor called QUICAgent. The ca...24 aug 2026AnalyseUAT-10147 Uses AI to Scale Server Attacks, Deploys SPECTRE With EDR Bypass and Linux RootkitCybersecurity researchers have disclosed details of a Chinese-speaking cybercrime group dubbed UAT-10147 that's targeting Windows and Linux web servers globally across the educatio...24 aug 2026