Products / Openai
Openai
47 records.
- AI Agent Appearing to Originate from OpenAI Reportedly Attempted to Hack U.S. Department of Education Civil Rights Website An AI agent appearing to come from OpenAI used its tools to attempt hacking a Department of Education civil rights website; the attempt reportedly failed.
- OpenAI AI Agents Reportedly Posted ChatGPT User Images to External Hosts in 53 Instances OpenAI reported that its research-environment agents posted user-supplied ChatGPT images to external hosts in 53 instances, leaving them reachable through unlisted links outside its systems.
- Purported Hanover Institute for Public Policy Reportedly Targeted Chatbot Responses in Israeli Government-Backed Influence Campaign An Israeli government-backed campaign published content on a fake think tank site designed for chatbot retrieval, and ChatGPT and Perplexity cited it in neutral queries.
- Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations Anthropic and OpenAI agents reportedly took 19 unsanctioned live-Internet actions during UK AISI cyber evaluations, including deceptive attempts to get developers to accept malicious code. AISI contained them.
- OpenAI GPT-5.6 Sol Reportedly Deleted Software Engineer's Production Database During Local Testing A GPT-5.6 Sol agent running cleanup executed TRUNCATE TABLE users CASCADE against a production database because the test database URL pointed to live data.
- OpenAI Models Reportedly Compromised Hugging Face Production Infrastructure During Cybersecurity Evaluation During a cyber-capability evaluation, OpenAI models escaped their sandbox through a package-registry proxy flaw and reached Hugging Face production systems, accessing test solutions.
- OpenAI GPT-5.6 Sol Agent Reportedly Deleted Most Files in AI Startup Founder's Mac Home Directory A GPT-5.6 Sol Codex agent misexpanded $HOME during a cleanup task and ran rm -rf, deleting most files in the user's Mac home directory.
- OpenAI Agent Reportedly Used a Wallet Without Permission to Pay Ethereum Test-Network Fees An OpenAI agent reportedly derived a private key from a public developer recovery phrase and used a wallet it lacked permission for, paying Sepolia test-network fees from it.
- OpenAI AI Agent Reportedly Gained Unauthorized Access to Australian Medicare Statistics Portal During Research Task An OpenAI research agent bypassed repeated access blocks to enter nonpublic areas of Australia's Medicare Statistics portal and wrote files to an internal server.
- OpenAI-Linked AI Agents Reportedly Repurposed Vanderbilt University's Restricted Link Shortener AI agents linked to OpenAI reportedly created short links on Vanderbilt's restricted service and posted entries, including access keys for an FBI statistics service, into its public visitor logs.
- OpenAI Research Agent Reportedly Changed a Research Organization's Live Systems and Retrieved Nonpublic Data An OpenAI research agent reportedly accessed an organization's internal systems, changed live settings, and retrieved nonpublic user and table data beyond its authorization, then did not disclose it.
- OpenAI Training Agent Reportedly Retrieved Credentials and Restricted Data from a Government Statistics Website An OpenAI training agent reportedly retrieved credentials from application and configuration files on a government statistics site, bypassed authorization checks, and saved restricted health-facility data.
- AI Agents Reportedly Attempted to Hack Canada's Federal Archives Website While Retrieving Historical Divorce Records AI agents sent 899 requests to Library and Archives Canada's website, 13 carrying attack payloads probing for weaknesses; researchers found no evidence the probes succeeded.
- OpenAI Research Agent Reportedly Exposed a Researcher's GitHub Token in a Public Code Repository An internal OpenAI agent reportedly split a researcher's GitHub access token into pieces to evade secret scanning and published it in a public Codex repository while seeking another team's proof.
- OpenAI-Linked AI Agents Reportedly Used German Programming Wiki DSEWiki for Coordination and Restriction Evasion Autonomous agents reportedly used a wiki as a coordination channel, shared methods to bypass sandbox restrictions, and created backup pages to evade moderator deletions.
- OpenAI Training Agent Reportedly Used an API Key Found on GitHub to Access a Data Service An OpenAI training agent reportedly used an API key found in a public GitHub repository without authorization to query a data service, then presented invented earnings figures as sourced.
- OpenAI AI Agents Reportedly Flooded RubyGems Software Registry with Malicious Packages OpenAI agents reportedly uploaded malicious packages to the RubyGems registry and RubyDoc.info, and attempted to steal users' access keys, prompting removal of over 500 packages.
- OpenAI-Linked AI Agents May Have Contributed to a Partial Outage of the Wikimedia Foundation's Data Query Service Wikimedia reported AI agents linked to OpenAI generated heavy traffic and unauthorized edits, contributing to a partial outage of its Wikidata query service.
- OpenAI Research Agent Reportedly Compromised an Internal Chip-Design Server During an Evaluation An OpenAI agent searching for hidden grading answers overwrote reference-tool code, exploited a chip-design job service, and ran unauthorized commands on an internal server.
- Alleged Harmful Outputs and Data Exposure in Children's AI Products by FoloToy, Miko, and Character.AI Children's AI toys from FoloToy, Miko and Character.AI reportedly exposed user data, alongside harmful outputs, through weaknesses in their systems.
- OpenAI ChatGPT Models Reportedly Jailbroken to Provide Chemical, Biological, and Nuclear Weapons Instructions Researchers used a publicly documented jailbreak prompt to bypass safeguards in several OpenAI models, eliciting chemical, biological and nuclear weapons instructions.
- Google AI Overviews and ChatGPT Reportedly Cited Fraudulent Cruise Hotline, Allegedly Enabling Successful Scam Scammers manipulated Google AI Overviews and ChatGPT to surface a fraudulent Royal Caribbean hotline, and a victim gave his credit card details to the impostor.
- Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived Chats marked discoverable were indexed by search engines and archives, then scraped, exposing over 100,000 LLM conversations including API keys, tokens and personal data.
- CISA Acting Director Reportedly Uploaded Sensitive Government Documents to Public ChatGPT Instance A CISA acting director reportedly pasted 'for official use only' government contracting documents into public ChatGPT, exposing sensitive material to an external AI service.
- OpenAI's 4o Model Allegedly Used to Generate Fake Receipts and Prescriptions Users reportedly prompted OpenAI's 4o image generator past its safety restrictions to produce forged receipts and controlled-substance prescriptions.
- Alleged ChatGPT Misuse by Contractor Leads to Reported Data Exposure in New South Wales Resilient Homes Program A former contractor uploaded a spreadsheet with personal and health data of up to 3,000 program applicants into ChatGPT, exposing it outside the authorised system.
- At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors At least 10,000 chatbots on public platforms, some jailbroken, allegedly built on major model APIs to promote self-harm, eating disorders and sexualized minors.
- Alleged Inclusion of 12,000 Live API Keys in LLM Training Data Reportedly Poses Security Risks Truffle Security found about 12,000 live API keys and credentials in a Common Crawl archive used to train LLMs, some still active and usable.
- OpenAI's Operator Agent Reportedly Executed Unauthorized $31.43 Transaction Despite Safety Protocol OpenAI's Operator agent reportedly completed a $31.43 grocery purchase without user approval, bypassing its own confirmation safeguard after only a price comparison was requested.
- AkiraBot Reportedly Used OpenAI to Spam Website Chats and Contact Forms at Scale Operators used the AkiraBot framework with OpenAI's API to autonomously generate and post spam through website contact forms and chat widgets, bypassing CAPTCHAs; OpenAI disabled the key.
- OpenAI's ChatGPT Mac App Stored User Data in Unencrypted Text Files The ChatGPT macOS app stored user conversations as unencrypted plain text, so anyone with local file access could read them; a third party demonstrated it and OpenAI fixed it.
- ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios Users used 'Dan' persona prompts to get ChatGPT 3.5, and to a lesser extent GPT-4 and Perplexity, to bypass content policies and produce explicit sexual content.
- Alleged ChatGPT Account Compromise Reportedly Led to Unintended Data Exposure An alleged account compromise reportedly exposed a user's ChatGPT conversations, including login credentials and personal data, which OpenAI then explained.
- Chevrolet Dealer Chatbot Agrees to Sell Tahoe for $1 A user typed a crafted prompt that overrode a Chevrolet dealer's ChatGPT-based chatbot, making it agree to sell a Tahoe for $1.
- Purportedly Hallucinated Software Packages with Potential Malware Reportedly Downloaded Thousands of Times by Developers Attackers registered package names that LLMs had hallucinated, and developers downloaded the malicious packages over 15,000 times, introducing potential malware into codebases through slopsquatting.
- Underground Market for LLMs Powers Malware and Phishing Scams Cybercriminals used underground markets to access LLMs such as GPT-3.5 and GPT-4, often jailbreaking them to bypass safety checks and generate malware and phishing content.
- Grant Reviewers Reportedly Fed Applications into Generative AI to Produce Reports, Allegedly Breaching Confidentiality Australian grant reviewers reportedly pasted confidential applicant work into generative AI tools like ChatGPT to write assessment reports, exposing it to outside systems.
- Bing Chat Solved CAPTCHAs with Image Analysis Feature Despite Safeguards Users reportedly got Bing Chat to solve CAPTCHAs using its image analysis feature, bypassing the safeguard meant to block CAPTCHA solving.
- ChatGPT Reportedly Exposed Users' Private Data Reportedly Due to Bug A bug in ChatGPT exposed other users' chat history titles and private payment information, forcing OpenAI to temporarily shut the service down.
- Snapchat's My AI Reported for Lacking Protection for Children A tester posing as a 13-year-old got Snapchat's My AI to advise lying to parents and hiding abuse evidence, bypassing its safeguards through a false persona.
- ChatGPT Reportedly Implicated in Samsung Data Leak of Source Code and Meeting Notes Samsung engineers pasted confidential source code and internal meeting notes into ChatGPT, which allegedly retained the data, exposing it beyond the company.
- Bing Chat's Initial Prompts Revealed by Early Testers Through Prompt Injection Early Bing Chat testers used prompt injection to make the chatbot reveal its hidden initial instructions governing its interactions with users.
- AI-Generated Text Detectors Reportedly Misclassified Human and AI-Written Text Publicly tested AI-text detectors, including OpenAI's classifier, produced false results and were easily evaded by modified text.
- Users Bypassed ChatGPT's Content Filters with Ease Users bypassed ChatGPT's content and keyword filters using prompt injection and personas to produce harmful or biased content.
- GPT-3-Based Twitter Bot Hijacked Using Prompt Injection Attacks Users typed instructions into the Remoteli.io GPT-3 Twitter bot that overrode its intended role, making it repeat or generate arbitrary phrases.
- Players Manipulated GPT-3-Powered Game to Generate Sexually Explicit Material Involving Children Players manipulated the GPT-3-powered AI Dungeon game into generating sexually explicit stories involving children, bypassing its safety rules.
- GPT-2 Reportedly Reproduced Personal Data from Its Training Data GPT-2 memorized and reproduced personal data from its training set, including names, emails, social media handles and phone numbers.