{"data":{"id":"0f9f9aab-9b8a-48fc-adb7-23dc3991d49c","title":"Security researchers used Claude to help them hack into OpenAI","summary":"Security researchers used Anthropic's Claude AI model to compromise OpenAI employee accounts and gain access to OpenAI's GitHub repository (a system for storing and managing code) within 72 hours. They demonstrated their unauthorized access by submitting a pull request (a request to add code changes) from a stolen employee account, though they did not access the internal code itself.","solution":"N/A -- no mitigation discussed in source.","labels":["security"],"sourceUrl":"https://www.theverge.com/ai-artificial-intelligence/997444/openai-hack-claude-heif-heist","publishedAt":"2026-09-18T15:30:16.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["supply_chain"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["OpenAI","Anthropic","Claude Opus","GitHub"],"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":"2026-09-18T15:30:16.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity"],"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}