{"data":{"id":"bc4c1074-87fc-47be-a08d-8fc12ae30671","title":"Breaking Claude Code Opus 5 Auto Mode","summary":"Researchers found a way to hijack Claude Code Opus 5 in Auto Mode, a feature that automatically executes code without asking the user for approval, achieving a 60-80% attack success rate through a simple website summary request. This contradicts Anthropic's own safety evaluation, which reported a 0% success rate for prompt injection attacks (tricking an AI by hiding malicious instructions in normal-looking input) against this mode. Auto Mode became the default setting for Claude Code in mid-August, making this vulnerability potentially affect many users.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://embracethered.com/blog/posts/2026/breaking-claude-code-opus-5-and-automode/","publishedAt":"2026-08-27T04:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["prompt_injection","jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Anthropic","Claude","Claude Code Opus 5"],"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":"2026-08-27T04:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}