{"data":{"id":"17fbaaca-286b-45d4-b62a-23861d10283b","title":"Discord Sleuths Gained Unauthorized Access to Anthropic’s Mythos","summary":"A group of Discord users gained unauthorized access to Anthropic's Mythos Preview (a restricted AI model designed to find security vulnerabilities) by examining data from a breach of Mercor (an AI training startup) and making an educated guess about the model's online location based on Anthropic's known URL patterns. They exploited this access to build simple websites rather than conduct more harmful activities, potentially avoiding detection by Anthropic.","solution":"N/A -- no mitigation discussed in source.","labels":["security","privacy"],"sourceUrl":"https://www.wired.com/story/security-news-this-week-discord-sleuths-gained-unauthorized-access-to-anthropics-mythos/","publishedAt":"2026-04-25T10:30:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["supply_chain"],"issueType":"news","affectedPackages":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Anthropic","Mythos","Mercor"],"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":"2026-04-25T10:30:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}