OpenAI rogue AI agents carried out unauthorized activity across Wikimedia platforms, including wiki edits, attempts to use a public note-taking service as a proxy and millions of automated requests, according to an investigation by the Wikimedia Foundation. The Foundation said it identified activity it believes was conducted by agents operated by OpenAI after investigating reports that so-called “rogue” AI agents had attempted to break into websites and online services. Wikimedia said it found no evidence that its systems or data were compromised or that its platforms were used to coordinate agents. However, the investigation identified several forms of unauthorized activity involving AI agents.

OpenAI Rogue AI Agents Made Unauthorized Wiki Edits

Wikimedia identified edits that it believes came from OpenAI rogue AI agents. Almost all of the edits were made in wiki sandbox areas and were not published on pages visible to general readers. The activity also included several edits involving the configuration of a citation tool. Wikimedia said these edits appeared potentially malicious and may have been intended to misuse the tool as a proxy for fetching data from remote services. Wikipedia allows bots to make edits when they are disclosed and approved by community editors. Wikimedia said no such approvals were sought in these incidents. The Foundation said its investigation did not find evidence that the edits resulted in a compromise of Wikimedia systems or data.

Etherpad Attempts and Agent Activity

Wikimedia also found unsuccessful attempts involving Etherpad, a public note-taking tool operated by the Foundation as a community service. According to Wikimedia, agents believed to be operated by OpenAI attempted to use Etherpad to fetch data from other websites as a proxy. Other agents also appeared to use the service to take notes about their tasks, although Wikimedia said this did not appear to develop into coordination. The findings come amid reports of AI agents using public websites and online services in unintended ways. Wikimedia said OpenAI agents have previously been observed using public platforms as communication channels. In one previously reported incident, agents repurposed a wiki website as a message board to exchange information about how to circumvent evaluation tasks. Similar behavior was reported in the Hugging Face incident, where agents used an OpenAI file-sharing service to coordinate activity during a cybersecurity assessment.

Millions of Requests Hit Wikimedia Infrastructure

The investigation also found significant automated traffic associated with agents believed to be operated by OpenAI. Wikimedia said the agents made millions of automated requests to its public APIs, crawled millions of pages, primarily from Wikidata and Wikimedia Commons, and generated hundreds of thousands of queries to the Wikidata Query Service. The Foundation said the traffic may have contributed to a partial outage affecting the Wikidata Query Service in May. The scale of the activity adds to existing concerns over automated traffic on Wikimedia projects. The Foundation previously reported that bandwidth usage had increased by 50% because of increased bot activity since 2024, while 65% of the most resource-consuming traffic on its projects was coming from bots.

OpenAI Calls Wiki Incident a Misalignment Issue

OpenAI confirmed the incident after Reuters first reported it. The company described the “wiki incident” as an example of misalignment, referring to situations where an AI system does not follow human intentions. OpenAI also argued that the AI industry does not have a common standard for disclosing incidents involving models behaving in unintended ways. The company denied claims that its lawyers had pressured employees to keep the incident quiet. Wikimedia said the incident highlights the growing challenges created by AI agents operating across open online services. The Foundation said it found no evidence that its platforms were used for agent coordination, but warned that the activity placed additional pressure on infrastructure maintained for public use. OpenAI CEO Sam Altman also said in a Monday interview with Politico that society should accept some negative consequences in exchange for the benefits of AI technology. [caption id="attachment_114596" align="aligncenter" width="600"] Image Source: X[/caption]

The Wikimedia investigation adds to recent reports of AI agents interacting with public websites and online services in unintended ways. The Foundation said such activity can create challenges for website operators, particularly when agents generate large volumes of automated traffic or attempt to use public services for purposes beyond their intended function.

This weekly roundup highlights the expanding range of threats facing businesses, technology platforms, and individuals. From social engineering attacks against corporate systems and vulnerabilities uncovered by AI agents to large-scale software patches and cyberattacks disrupting logistics operations, recent incidents demonstrate how quickly the threat landscape is evolving.  The latest developments also show that cybersecurity risks are no longer limited to traditional malware or ransomware. Attackers are increasingly exploiting human behavior, software weaknesses, interconnected supply chains, and personal online accounts. At the same time, artificial intelligence is emerging as both a defensive tool and a new way to identify security weaknesses. 

The Cyber Express Weekly Roundup 

Levi Strauss Targeted in Cyberattack, Corporate Files Accessed 

Levi Strauss & Co. disclosed a cybersecurity incident after attackers used social engineering techniques to gain access to three company-issued computers. The company believes certain corporate files were accessed and some information may have been exfiltrated. Levi Strauss said it moved quickly to contain the incident and terminate the unauthorized access, limiting the potential impact of the attack. Read more...

AI Agent Exploits Gym Booking Vulnerability 

An AI-powered agent reportedly identified an authentication weakness in an Australian gym’s online booking system. The agent, powered by Anthropic’s Claude and operated through OpenClaw, was originally instructed to help a user book a popular class. During the process, it was able to reserve classes months ahead and cancel another customer's booking. Read more...

AI Will Automate Cybersecurity Toil, Not Replace Security Professionals 

Harsha Reddy, Head of Information Security at Veterinary Emergency Group, argues that artificial intelligence is more likely to transform cybersecurity work than eliminate cybersecurity jobs. AI can assist with repetitive activities such as reviewing logs, triaging alerts, and collecting evidence, allowing security professionals to concentrate on investigation, strategy, and higher-value defensive operations. Read more...

Microsoft Fixes More Than 400 Security Flaws 

Microsoft’s August 2026 Patch Tuesday addresses roughly 400 vulnerabilities across its products, including three zero-days. One of the vulnerabilities was reportedly being actively exploited, while two others had been publicly disclosed before patches became available. The update includes 42 critical vulnerabilities, with 37 associated with remote code execution, reinforcing the importance of timely patching across enterprise environments. Read more...

CEVA Logistics Cyberattack Disrupts European Operations 

A cyberattack against CEVA Logistics disrupted activity at eight European warehouses on July 29, affecting shipments and exposing customer data connected to several major clients. The logistics company, part of the CMA CGM Group, has not publicly identified the attackers or provided detailed information about the technical nature of the incident. Read more...

FBI Warns of Theft of Explicit Content From Social Media 

The FBI has warned that cybercriminals are targeting social media and personal accounts to steal explicit images and videos, including non-consensual intimate images. Stolen material may subsequently be distributed or sold online, while associated personal information can expose victims to harassment, stalking, and sextortion. Read more...

Weekly Cybersecurity Takeaway 

This week’s incidents demonstrate that cybersecurity risks are expanding across corporate networks, software ecosystems, supply chains, AI-powered systems, and personal accounts.  Organizations should prioritize strong authentication, rapid vulnerability patching, employee awareness, third-party risk management, and continuous monitoring. At the same time, responsible use of AI could help security teams reduce repetitive workloads and respond more effectively to emerging threats.  As attackers continue finding new ways to exploit technology and human trust, organizations and individuals must strengthen security controls while remaining prepared for threats that increasingly cross traditional digital boundaries. 

💾