{"data":{"id":"7652dfef-9091-4f33-b9d2-b26efe3fb389","title":"Auto mode is now the default in Claude Code for Pro, Max, and Team plans","summary":"Anthropic has made auto mode (an automated decision-making feature in Claude Code) the default setting for Pro, Max, and Team users starting August 14th, claiming it blocks 89% of harmful actions compared to human approval alone. The company published evaluation results showing that in 720 prompt injection (attacks where malicious instructions are hidden in external content) attempts against Claude models, none succeeded when auto mode was enabled, though the author expresses concerns about whether this protection covers all possible attack scenarios.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","security"],"sourceUrl":"https://simonwillison.net/2026/Aug/8/auto-mode/#atom-everything","publishedAt":"2026-08-08T22:36:03.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Anthropic","Claude","Claude Code","Claude Fable 5","Claude Opus 5","Claude Sonnet 5","Codex"],"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":"2026-08-08T22:36:03.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}