{"data":{"id":"93307abe-98b6-44ca-94e6-de045dce8258","title":"Free Chinese AI Models Are Getting Scary Good at Hacking","summary":"Vals tested AI models on multi-step attacks against simulated corporate networks and found that open-weight models now come close to closed ones. OpenAI's restricted Daybreak completed 81 percent of tasks on average, while DeepSeek completed 73 percent, and Vals estimates an attack costs $17 to $46 in tokens with GPT-6-Sol versus $2 to $3 with DeepSeek.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://www.wired.com/story/free-chinese-ai-models-are-getting-scary-good-at-hacking/","publishedAt":"2026-11-06T18:43:43.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["DeepSeek","GLM","OpenAI Daybreak","GPT-6-Sol","Claude Mythos Preview","Project Glasswing"],"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":"2026-11-06T18:43:43.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}