A design flaw in Anthropic’s Claude Dispatch feature let a malicious browser extension run commands on the operating system, even on a different computer. Researchers at Forever Security named the attack ThisBash. They found that Claude Dispatch accepted instructions from an ordinary logged-in claude.ai session. An extension that could control... Weiterlesen: Claude AI Flaw Lets Malicious Browser Extensions Execute Commands on …
Intelligence View
⚡ tsecurity.de Intelligence
Claude AI Flaw Lets Malicious Browser Extensions Execute Commands on Remote Computers
A design flaw in Anthropic’s Claude Dispatch feature let a malicious browser extension run commands on the operating system, even on a different computer. R…
Ethical Hacking GBHackers Security | #1 Globally Trusted Cyber Security News Platform 1 Min. Lesezeit
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!
Powered by tsecurity.de
tsecurity.de Hub
Intelligence Digest — free The top security news daily · unsubscribe anytime
Community Rating & Social Proof
⭐ Leser-Wertung
–
Ø / 5.0
★★★★★
No reader ratings yet
Was this page helpful?
0
Powered by tsecurity.de
tsecurity.de Hub
Related story clusters & sources (vector AI)
8 sources
OpenAI will mit GPT-6 Cyber das Aufspüren von Sicherheitslücken erleichtern – doch es gibt auch Kritik
7 more sources
IIT-Administrator3 hours agoOpenAI schickt GPT-6 Cyber auf Bug-Jagd CCyberInsider2 hours agoOpenAI launches new GPT-6 Cyber model that found 81 flaws on Firefox IIT Security News37 min. agoOpenAI Rates GPT-6 Cyber Critical After Major Vulnerability Discoveries SSecurity Affairs1 hour agoOpenAI Rates GPT-6 Cyber Critical After Major Vulnerability Discoveries HHelp Net Security3 hours agoOpenAI’s GPT-6 Cyber found 81 Firefox flaws earlier AI testing missed GGoogle Alert1 hour agoGPT-6 Cyber: OpenAI-Modell für Sicherheitsforschung - All About Security
+1
7 sources
[NEU] [UNGEPATCHT] [mittel] Ansible: Schwachstelle ermöglicht Offenlegung von Informationen
6 more sources
BBSI Warn- und Informationsd…54 min. ago[NEU] [mittel] Langflow: Schwachstelle ermöglicht Denial of Service BBSI Warn- und Informationsd…54 min. ago[NEU] [mittel] QT: Schwachstelle ermöglicht Offenlegung von Informationen BBSI Warn- und Informationsd…54 min. ago[NEU] [mittel] Angular: Schwachstelle ermöglicht Offenlegung von Informationen BBSI Warn- und Informationsd…54 min. ago[NEU] [mittel] LibreOffice: Schwachstelle ermöglicht Denial-of-Service BBSI Warn- und Informationsd…54 min. ago[UPDATE] [mittel] dbus: Schwachstelle ermöglicht Denial of Service BBSI Warn- und Informationsd…51 min. ago[UPDATE] [mittel] Keycloak: Schwachstelle ermöglicht Erlangen von Administratorrechten
6 sources
USN-9002-1: Linux kernel (NVIDIA Tegra) vulnerabilities
5 more sources
UUbuntu security notices2 hours agoUSN-9003-1: Linux kernel (NVIDIA) vulnerabilities VVulDB Updates1 hour agoCVE-2022-4128 | Linux Kernel MPTCP Protocol null pointer dereference (EUVD-2022-51493) VVulDB Updates1 hour agoCVE-2022-4129 | Linux Kernel L2TP net/l2tp/l2tp_core.c sk_user_data null pointer dereference (FEDORA-2022-24041b1667 / EUVD-2022-51494) VVulDB Updates47 min. agoCVE-2025-39916 | Linux Kernel up to fd3e613a912bbb344ee18579cc2ad3329aacba41 damon_reclaim_apply_parameters divide by zero (EUVD-2025-31835 / Nessus ID 269681) VVulDB Updates47 min. agoCVE-2025-39891 | Linux Kernel up to 6.16.5 mwifiex_init_channel_scan_gap privilege escalation (Nessus ID 274583 / WID-SEC-2025-2170)
Mehr aus dieser Kategorie
Blättern: Pfeiltasten [ ← ] [ → ] · Tasten j / k · mobil: Wischen
HAND-OFF
Auf Smartphone übergeben (ADVISORY)
Scannen Sie den QR-Code mit der Smartphone-Kamera für sofortigen mobilen Zugriff:
https://tsecurity.de/en/4323841/ethical-hacking/claude-ai-flaw-lets-malicious-browser-extensions-execute-commands-on-remote-computers/