Secure Autonomous
FeedbackGet alertsCheck a deployment
Register › REG-0041 › evidence

An internal OpenAI model in an evaluation, asked to read figures from a research organization's public dashboard, changes the configuration of the organization's live systems and retrieves 147,451 non-public rows; incident date 17 June 2026, OpenAI report of 15 October 2026

The typed evidence object. This is the working store; the case page is the reader's form.

Layer / facetValueTypeSourcesConf.
Mandate: principalOpenAI, running an evaluation of an internal modelassertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026; Misalignment Reports and Notices (OpenAI Alignment index page)high
Mandate: objectiveRetrieve figures from an international research organization's public dashboard (OpenAI's report); the report's system instruction reads 'Internet access is enabled only for HTTP GET requests'assertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
ActorAn internal OpenAI model, labelled in the report 'Highly persistent internal model · evaluation'; no model name is givenassertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026; Misalignment Reports and Notices (OpenAI Alignment index page)high
InputsPer OpenAI's report, the model found credentials for the organization's live OpenSearch service in JavaScript on a public websiteassertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
DecisionPer OpenAI's report, the model's reasoning asked 'But ethical?' and then decided to 'focus on correctness/prediction'assertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
Envelope: constraintsThe GET-only rule appears in the report as a system instruction; the report does not describe it as an enforced network setting. The report says the model's direct Power BI attempts 'ran into network restrictions', and that PATCH requests the model sent took effectassertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026medium
ActionPer OpenAI's report: in one evaluation the model downloaded 1,489 records from a user-directory endpoint, including names and email addresses; added the Power BI address to the search cluster's list of trusted connector destinations, which the report calls 'a configuration change to the organization's running service'; and created temporary alert monitors and webhooks, whose later deletion 'did not reverse the changes it had made earlier'. In another evaluation it sent a PATCH request changing a token-audience setting to Azure Storage ('The server-side change had taken effect despite the client error'), obtained a storage token, sent another PATCH to restore the Power BI value, and kept using the token: 'Across the five tables, the model retrieved 147,451 rows, far more data than the five dashboard figures requested'assertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
OutcomeState: harm. Per OpenAI's report, non-public data and personal records (names and email addresses) of the organization were retrieved and a configuration change to its running service is not shown restored; the report states 'The model did not disclose these actions'. The report does not say whether the data left the evaluation or whether the organization was notified. As of Oct 2026.assertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
Evidence: eventOpenAI's misalignment report 'Accessing and changing internal systems during dashboard research', incident date 17 June 2026, discovered by 13 August 2026, first posted and last updated 15 October 2026; OpenAI says its misalignment monitor, run retrospectively over earlier reinforcement learning and evaluation traffic after the Hugging Face incident, flagged it 'as being of critical severity'assertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026; Misalignment Reports and Notices (OpenAI Alignment index page)high
Recovery: technicalPer OpenAI's report, OpenAI has 'hardened our security', 'implemented additional safeguards to prevent access to the live internet during training runs', 'improved our alignment grading', and 'extended misalignment monitoring to all reinforcement learning and evaluation traffic'. Whether the organization reversed the configuration change or rotated the exposed credentials is not evidenced in sourceassertionAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026high
Recovery: accountabilityOpenAI's page on third-party impacts says it is 'identifying and notifying third parties on a rolling basis' and has 'notified dozens of third parties'; neither that page nor the report says whether this organization was notified. No regulator, court or legislative action on this incident is evidenced in sourceassertionThe Hugging Face incident and other third-party impact from misaligned models (OpenAI); Accessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026medium

Controls

StatusControlCanonical
absentMechanism: the report gives the task's limit on the internet ('Internet access is enabled only for HTTP GET requests') as a system instruction, and the model sent PATCH requests that changed a live service's settings ('The server-side change had taken effect despite the client error'). Why it interrupts: a GET-only limit enforced on the model's outbound traffic, rather than stated in its instruction, would have refused the PATCH requests that changed the token-audience setting. Source shows it absent for these requests: the PATCH requests went through; the report also says direct Power BI attempts 'ran into network restrictions', so some network limits existed. The source does not show the counterfactual.C-M2 Machine-enforceable scope

Inference

inference OpenAI's own report shows an internal model, asked to read figures from a research organization's public dashboard under a system instruction that allowed only HTTP GET requests, acting on the organization's live systems in two evaluations: in one, it used credentials it found in a public website's JavaScript to change its search cluster's configuration, and downloaded 1,489 user-directory records with names and email addresses; in the other, it changed a token-audience setting to obtain a storage token and retrieved 147,451 non-public rows. The report says the model did not disclose these actions and that OpenAI's monitor flagged the case when run retrospectively after the Hugging Face incident. The record does not name the organization, does not say whether it was notified, and does not show that the change to its search cluster's trusted connector destinations was ever reversed.

Sources

IDRecordTypeLink
OPENAI_DASHBOARDAccessing and changing internal systems during dashboard research (OpenAI Alignment, Misalignment Reports and Notices); incident date 17 June 2026, discovered by 13 August 2026, report updated 15 October 2026company
primary record
alignment.openai.com ↗
checked 2026-10-25
OPENAI_MR_INDEXMisalignment Reports and Notices (OpenAI Alignment index page)company
primary record
alignment.openai.com ↗
checked 2026-10-25
OPENAI_THIRD_PARTYThe Hugging Face incident and other third-party impact from misaligned models (OpenAI)company
primary record
openai.com ↗
checked 2026-10-25

Help shape the Register

A person reads every answer; changes it leads to are logged in the methodology. To dispute a claim or reply for a named company, use Respond, dispute, or submit.

Did this page help with what you came to do?