OpenAI Workspace Agents Vulnerability: A Single ChatGPT Link Can Create a Malicious AI Agent
Original title:One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes
AI summary
Security firm Zenity Labs found an "AgentForger" vulnerability in OpenAI Workspace Agents: an attacker can send a ChatGPT link containing a malicious prompt to create an autonomous AI agent under the victim's account. The agent inherits the victim's identity and authorized app permissions, bypasses security approvals, and sets a scheduled task running every five minutes to fetch instructions from the attacker's mailbox. OpenAI fixed the vulnerability within four days.
Key Takeaways
- Security firm Zenity Labs found an "AgentForger" vulnerability in OpenAI Workspace Agents: an…
- The agent inherits the victim's identity and authorized app permissions,bypasses security…
- OpenAI fixed the vulnerability within four days.
Quick Facts
- Published
- Updated
- Source
- The Decoder:AI News(RSS)
- Category
- Industry
- AI score
- 70
这不是普通漏洞,是攻击者仅用一个链接就能在受害者身份下创建自主代理的新攻击类型,传统安全工具完全看不见。所有用 ChatGPT Workspace 并连接了企业应用的公司都应该认真读一遍。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenAI Workspace Agents Vulnerability: A Single ChatGPT Link Can Create a Malicious AI Agent. July 24, 2026. https://new.nat6.net/en/news/cmrxs4yyw01xkroxpom7zfjvc/