{"data":{"id":"b74d7245-3deb-42c7-b4a1-7e7f3d4aa02d","title":"OpenAI’s Astra Becomes First Model to Cross Critical Cybersecurity Threshold","summary":"OpenAI's new model, Astra, has reached a 'Critical' cybersecurity capability level, meaning it can independently find and exploit zero-day vulnerabilities (previously unknown security flaws) across well-defended systems or carry out complete cyberattacks from basic instructions. The company says additional safeguards are required before release, and full cybersecurity capabilities will initially be limited to a testing group through the Daybreak Blue program, with wider availability coming later.","solution":"OpenAI plans to give a group of testers early access to Astra's cybersecurity capabilities, with wider availability to follow through its Daybreak Blue program. The company emphasizes the need for 'stronger evidence of aligned behavior, safeguards that keep pace with capability, and a willingness to slow down when those protections are not sufficient.'","labels":["security","safety"],"sourceUrl":"https://www.securityweek.com/openais-astra-becomes-first-model-to-cross-critical-cybersecurity-threshold/","publishedAt":"2026-09-02T10:38:13.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_theft","jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","Astra","GPT-5.6 Sol","Daybreak Blue"],"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":"2026-09-02T10:38:13.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}