Known CVEnpm/@anthropic-ai/claude-code
CVE-2025-59536: Claude Code runs project commands before the startup trust dialog
High
Opening an untrusted repository could run commands from its project configuration before the user accepted the trust prompt. Fixed in 1.0.111.
Affected and fixed versions
Affected: < 1.0.111. Fixed in 1.0.111.
Sources
See every known CVE, and the ones in the news, in the Learning Center