{"data":{"id":"0664beb2-ffc2-4a48-b581-a6af765e488b","title":"OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot","summary":"Hacktron AI, a US-based startup, used Anthropic's Claude chatbot, and mainly OpenAI's GPT-5.6 Sol model, to compromise several OpenAI employees' ChatGPT accounts through an internal staff discussion forum hosted on Discourse. The researchers then made a harmless pull request to OpenAI's service on GitHub, reaching access to the software cache, though they say they viewed but did not download the code. Hacktron reported the work under an OpenAI bug bounty program and received $6,500.","solution":"N/A -- no mitigation discussed in source.","labels":["security","industry"],"sourceUrl":"https://www.theguardian.com/technology/2026/sep/18/openai-hacked-anthropic-claude-chatbot","publishedAt":"2026-09-18T11:20:44.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"low","attackType":["other"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["OpenAI","Anthropic","Claude","ChatGPT","GPT-5.6 Sol","Hugging Face"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-09-18T11:20:44.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}