NewsThe Register — Security
ChatGPT blindly trusts browser content, turning the page into a payload
Teaser from the source
You and me go ChatGPhish-ing in the dark
This is the RSS-feed teaser. Read the full article at the original source.
Read at The Register — SecurityMore on ChatGPT
Other advisories
- Highosv:MAL-2026-18057Malicious code in chatgpt-pro-activator (npm)
- Highosv:MAL-2026-18056Malicious code in chatgpt-desktop-setup (npm)
- Highosv:MAL-2026-18053Malicious code in @decoopus/chatgpt-setup (npm)
- Highosv:MAL-2026-18058Malicious code in chatgpt-pro-setup-tool (npm)
- HighCVE-2026-105238ChatGPTNextWeb NextChat: Server-Side-Request-Forgery (SSRF)
- Not ratedosv:CVE-2026-105238ChatGPTNextWeb NextChat Proxy Fallback proxy.ts proxyHandler server-side request forgery
- HighCVE-2026-105238In ChatGPTNextWeb NextChat bis 2.
- HighCVE-2026-82639ChatGPTNextWeb NextChat: unzureichende Eingabevalidierung
Other news entries
- Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User InteractionNewsThe Hacker News
- ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data ExfiltrationNewsCheck Point Research
- OpenAI says it's doubling Pro usage limits and bringing Work features to ChatNewsBleepingComputer
- A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private ChatsNewsThe Hacker News
- OpenAI doubles ChatGPT Pro usage limits after backlash over planned 50% cutNewsBleepingComputer
- Fake ChatGPT and Claude Apps Abuse Signed Executables to Deploy Crypto MinersNewsThe Hacker News
- Fake ChatGPT, Claude apps spread malware via signed AI binariesNewsCSO Online
- Tricks from the Past deployed via signed ChatGPT and Claude binariesNewsCheck Point Research
ID