NEWS
Vulnerability found in Claude Code Auto Mode against prompt injectionJohann Rehberger discovered an attack vector in which Auto Mode, the feature Anthropic uses by default to prevent prompt injections, allowed the execution of malicious code while blocking cleanup commands. This is a news summary compiled for the AiPulse newsletter — not the original article. The original article is at simonwillison.net. Read the original article AI Critique → English (automatic translation) |