AINewsnow

Malicious ChatGPT Share Link Could Run Attacker Code and Expose Private Chats

Researchers reported a ChatGPT bug, earning a $5,000 bounty, in which a malicious share link could run attacker code in the logged-in session of anyone who opened it, exposing private conversations. The flaw involved MathLive, which now checks origins in version 0.111.2.

Read the full story at Techmeme ↗

Timeline · 5 reports

  1. 2026-11-02 04:19 · DEV Community — AI
    How to Turn a ChatGPT Share Link into a PDF (and What’s in the Snapshot)
  2. 2026-11-01 01:07 · DEV Community — AI
    A ChatGPT Share Link Hijacks Accounts, and Malware Now Ranks Victims by Worth
  3. 2026-10-31 23:01 · DEV Community — AI
    A ChatGPT Share Link Could Run Code Through MathLive. MathLive 0.111.2 Now Checks Origins
  4. 2026-10-31 19:01 · Techmeme
    Researchers are paid $5K for reporting a bug to OpenAI that would let attackers run code in logged-in sessions of all who opened the hacker's ChatGPT share link
  5. 2026-10-31 05:33 · The Hacker News (security)
    A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private Chats

More stories

  1. OpenAI lowers funding target for new round to $20 billion — Financial Times AI
  2. Beginner's 15-minute lesson plan aims to teach ChatGPT basics to new users — Tom's Guide AI
  3. Google, Microsoft, OpenAI and Anthropic to honor shared robots.txt opt-out for AI training — OpenAI News
  4. OpenAI tightens ChatGPT limits on weapons information for teen users — Reuters AI
  5. Cognizant forms OpenAI Frontier Capability Group with over 25,000 professionals — The Globe and Mail
  6. OpenAI Raises Less Than Half of $30 Billion Target in Latest Round — Wall Street Journal Technology
  7. OpenAI unveils Community Safety Report and new teen protections in ChatGPT — OpenAI News
  8. Patrick Stewart was thinking about AI ethics years before ChatGPT launched — Fast Company AI

Get the daily brief of stories like this at 6:30 every morning →