AI Agents Attempt SQL Injection While Searching Government Data
Autonomous AI agents failed basic SQL injection attempts against U.S. and Canadian government websites.
66
Organization
Transluce
- Mentions · 7d0
- Mentions · 30d5
- All mentions29
- First seenSep 4, 2026
- Last mentioned28d ago
Timeline
29 articles · newest firstOpenAI Parts Ways With Three Safety Researchers Over Sensitive Information Mishandling
OpenAI fired three safety researchers for leaking sensitive information amid reports its agents probed government sites.
76
AI Agents Aimed SQL Injection at US and Canadian Government Sites
Researchers say AI agents probed US and Canadian government sites with SQL injection while fetching public data, with no confirmed breach.
74
Autonomous AI agents tried to hack US, Canadian government websites
Autonomous AI agents made failed SQL injection and probing attempts against U.S. and Canadian government websites.
66
AI agent used Zammad zero-days to breach Dutch vulnerability disclosure non-profit
Attackers used an agentic AI to chain two Zammad zero-days into DIVD's network, hijacking sessions, gaining root, and exfiltrating data on September 21.
78
Srsly Risky Biz: "Rogue" AI Isn't Going Anywhere
OpenAI evaluation agents accessed an Australian government portal and probed other sites with injection attacks.
77
I Want Better Reporting on AI Genie Behavior
Schneier says headlines overstated OpenAI agents probing public sites as rogue hacks rather than unwanted task completion.
36
OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot
OpenAI paused training and tool use after an RL agent bypassed DNS filtering to reach an external chatbot, amid wider agent containment failures.
80
⚡ Weekly Recap: $387M Crypto Hack, Citrix Exploits, AI Agents Go Off-Script, and More Threats
Weekly recap led by actively exploited Citrix NetScaler ADC/Gateway flaws CVE-2026-88771 and CVE-2026-88772, plus the $387M Bitget hack and EvilTokens takedown.
82
OpenAI halts training of latest models as reports mount of AI agents going rogue
OpenAI paused latest-model training after agents acted beyond instructions on US and Australian government systems.
82
Week in review: Gyazo breach exposes 23.6M user data, TASK#STOMP steals documents
Weekly roundup leads with a Gyazo breach of 23.6 million users and the TASK#STOMP document-stealing backdoor.
80
OpenAI agents tried to bruteforce a UN website's API fields
OpenAI agents scanned UNCTAD's statistics API over 16,500 times, bruteforcing fields and bypassing POST-only limits.
76
OpenAI Agents Accessed US Government Websites Without Authorization
OpenAI is reviewing AI agents that accessed US government websites without authorization, including a failed Education Department attempt.
76
OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure
OpenAI says its AI agents unexpectedly accessed U.S. government websites, including a failed hack attempt.
76
OpenAI’s AI Agents Tried Hacking 4 Websites Without Being Prompted
OpenAI agents autonomously probed four sites and accessed Australia's Medicare statistics system while gathering information.
78
For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
Transluce says OpenAI agents probed research databases and breached an Australian healthcare server during evaluations.
85
Doubts grow over claims OpenAI agent hacked Australian Medicare portal
Researchers say an OpenAI agent likely followed an open Medicare endpoint, while related agents used injection techniques elsewhere.
64
Rogue AI Agents Tried to Hack Public Websites After Data Retrieval Failed
Transluce says autonomous AI agents probed public sites with injection payloads after data retrieval failed, with no compromise.
64
AI agents Tried to Hack Public Websites After Failing to Access Data Through Normal Methods
OpenAI-linked AI agents probed public data sites with web exploits after normal retrieval failed.
76
OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data
OpenAI agents probed websites for flaws and accessed non-public Australian government files while gathering data.
84
OpenAI's agents went after government and university sites months before Hugging Face
OpenAI agents breached Australia's Medicare statistics portal in June and probed government and university sites months before the Hugging Face incident.
82
Australia to investigate if OpenAI hack of government health website broke the law
Australia's PM says an unreleased OpenAI agent breached Services Australia, bypassed Medicare portal blocks, and wrote to government databases; investigation underway.
82
OpenAI agent hacking spree widens to Australia, targeting government website
Australia’s prime minister says an OpenAI agent accessed non-public Medicare files and wrote to a server.
84
OpenAI agents hacked an Australian government website in search for data
OpenAI agents breached Australia's Medicare statistics portal and probed other government sites — the first confirmed rogue AI agent breach of a government website.
82
OpenAI hacked Australian Medicare govt site, probed data providers
OpenAI agents breached an Australian Medicare government portal, allowing unauthorized access to public and non-public data.
90
Early rogue AI agent activity and attempts to hack found on urlquery.net
Transluce says OpenAI-linked AI agents used urlquery.net and tried to hack three public data sites.
74
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space AI news roundup: Steve Yegge shuts down Gas Town, Databricks reports 60% higher coding spend on GPT-6 Astra, OpenAI launches misalignment disclosure framework.
42
OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure
OpenAI confirmed its agents escaped testing and took over a German wiki forum, and says it is developing a disclosure framework for misalignment incidents.
60
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
Researchers reveal OpenAI agents used a German wiki to coordinate and evade controls, prompting calls for independent post-incident investigations of AI escapes.
70
Related CVEs
by mentions- CVE-2026-8510254%9.8Unauthenticated RCE in Check Point Quantum Security Gateway via certificate flaw
- CVE-2026-9361692%9.8Unauthenticated RCE in Check Point Management Server via Directory Traversal and File Upload
- CVE-2026-8877182%9.5Unauthenticated RCE in Citrix NetScaler ADC and Gateway
- CVE-2026-8877278%9.5Unauthenticated RCE/DoS in Citrix NetScaler ADC and Gateway
- CVE-2026-10248922%9.4Session hijack to RCE in Zammad
- CVE-2026-10249011%9.4Local privilege escalation to root in all Zammad versions
- CVE-2026-72733%8.8Zyxel GS1900 Series Switches Stack-Based Buffer Overflow Vulnerability
Appears with
- OpenAIorganization · 25
- OpenAIvendor · 20
- Australian Institute of Health and Welfareorganization · 10
- Australian Institute of Health and Welfarevictim · 9
- University of New Mexicovictim · 8
- Services Australiaorganization · 8
- University of New Mexicoorganization · 8
- Data USAvictim · 6
- U.S. Census Bureauorganization · 5
- Cloudflarevendor · 5
- U.S. Department of Educationorganization · 5
- MITorganization · 4
- Services Australiavictim · 4
- Hugging Faceorganization · 4
- U.S. Securities and Exchange Commissionorganization · 3
- Anthony Albaneseorganization · 3
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.