Zenity Labs discovered "AgentForger," a vulnerability in OpenAI's Agent Builder that allowed a single manipulated ChatGPT link to create an autonomous agent impersonating an employee. The agent inherited the victim's identity and access rights, bypassed approval requirements through a malicious prompt, and retrieved new instructions from the attacker's inbox every five minutes.
Summaries like this, in your inbox every morning.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Sens. Jim Banks and Adam Schiff secured a narrow antitrust exemption letting AI companies share intelligence a…
Carter Leffen, a product development coach at Bloomberg LP, says OpenAI's GPT-6 Astra worked about ten hours t…
Liam Dunne and Ben Moore of Discover Labs said AI search has shifted buyer behavior because people now consume…
OpenAI said on September 8 an unreleased internal model resolved Navier–Stokes existence and smoothness, a Mil…
Huawei unveiled the OceanStor M900 at Huawei Connect 2026, a petabyte-scale key-value (KV) cache system design…
Cloudflare announced its "Disallow AI Training" setting on September 15, available to all customers on all pla…
