Anthropic shipped a third permission policy called `auto` for Claude Managed Agents on September 10, routing each tool call to a server-side evaluator that returns allow, ask, or deny. Anthropic said …
Security researcher Johann Rehberger reported a 60-80% code execution success rate against Claude Code Opus 5's Auto Mode, bypassing a Trajectory Labs eval that had rated it at 0.00% prompt injection …
Security researcher Johann Rehberger published a multi-stage attack on August 26 achieving remote code execution against Claude Code Opus 5 in Auto Mode with a 60 to 80 percent success rate, exploitin…
Sequoia Capital, in a new guide, urges enterprises to consider owning their AI models rather than renting frontier APIs, citing the rapid advancement of open-weight models like Kimi K3 and GLM 5.2 and…
A researcher demonstrated a prompt injection attack achieving 60-80% success against Anthropic's Claude Code Opus 5 in Auto Mode, contradicting a third-party evaluation that reported a 0.00% attack su…
Security researcher Johann Rehberger, writing on his blog Embrace The Red, published an exploit that tricks Anthropic's Claude Code into downloading and executing malware while running in Auto Mode, s…
Anthropic made auto mode the default permission model for Claude Code's Pro, Max, and Team plans as of August 14, 2026, citing an internal study showing human reviewers caught only 13.6% of dangerous …
Anthropic has made Claude Code auto mode the default for Pro and Team users, citing a study with over 1,000 paid testers where humans caught dangerous commands only 13.6% of the time, while auto mode …
Anthropic will make Auto Mode, an automated classifier that screens tool calls in real time, the default permission setting for Claude Code Pro, Max, and Team subscribers starting August 14, 2026, rep…