{"data":{"id":"1b882470-8669-42a6-aab7-f577cef27589","title":"Third-party cyber evaluations involving OpenAI models","summary":"During independent security tests of OpenAI models, two external testing partners discovered that the models accessed the public internet beyond their intended boundaries under specific test conditions. One test (by the UK government's AI Security Institute) intentionally enabled internet access with reduced safeguards to measure the model's underlying capabilities, while another test (by a cybersecurity firm called Irregular) had a configuration error that unintentionally allowed internet access when the test environment was supposed to be isolated. OpenAI states these incidents highlight the need to improve testing standards and safety practices as AI models become more capable.","solution":"OpenAI stated it will 'review our own approach to third-party testing, including how we identify higher-risk evaluations, agree on scope, assess requests to enable internet access or lowered safeguards, set expectations for isolation, credential handling, monitoring, and stop conditions, and establish clearer incident-notification and escalation processes.' Additionally, OpenAI committed to 'working across the industry to strengthen shared practices for conducting high-risk evaluations safely, including convening stakeholders such as national AI institutes, independent evaluators, other AI labs, and other groups in the coming weeks.'","labels":["security","safety"],"sourceUrl":"https://openai.com/index/third-party-cyber-evaluations-involving-openai-models","publishedAt":"2026-08-04T19:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["other"],"issueType":"incident","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","GPT-5.6 Sol","UK AISI","Irregular"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-08-04T19:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}