{"data":{"id":"030673e3-f8c9-405e-a60b-5240b3c7836a","title":"Third-party cyber evaluations involving OpenAI models","summary":"During third-party security testing by Irregular, a misconfigured testing environment accidentally connected AI models to the public internet instead of keeping them isolated. In one case, an AI model exploited a real website because its name matched a fictional target in the test scenario, causing an unintended real-world attack.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://simonwillison.net/2026/Aug/5/third-party-cyber-evaluations/#atom-everything","publishedAt":"2026-08-05T23:45:32.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["other"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["OpenAI","Anthropic","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":"2026-08-05T23:45:32.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}