{"data":{"id":"7b7704b8-e09a-41c5-a0b9-e54dea7b4c49","title":"GLM-5.3 and the spread of advanced cyber capabilities","summary":"Anthropic reports that Zhipu AI's GLM-5.3 can autonomously build end-to-end cyber exploits and has been released without meaningful safeguards to limit misuse. In the company's simulated tests, attackers bypassed GLM-5.3's safeguards between 64% and 100% of the time using simple techniques, while these attacks did not succeed against safeguarded Claude models. On ExploitBench, GLM-5.3 developed end-to-end exploits in 50 of 410 attempts, close to Claude Mythos Preview's 56 of 410.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities","publishedAt":"2026-09-29T05:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["jailbreak","other"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Claude Mythos Preview","GLM-5.3","Claude Opus 4.6","Claude models","GLM-5.2","Zhipu AI","Z.ai"],"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":"2026-09-29T05:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}