Claude Code can execute commands prior to the startup trust dialog

概要

参考情報

• anthropics/claude-code security advisory · WEB
• nvd.nist.gov/vuln/detail/CVE-2025-59536 · ADVISORY
• anthropics/claude-code · PACKAGE

claude code のその他の脆弱性

• CVE-2026-55607高 8.8Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git…
• CVE-2026-46406中 6.1Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable…
• CVE-2026-54316緊急 9.1Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname f…
• CVE-2026-40068高 8.8In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validati…
• CVE-2026-39861緊急 10.0Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating syml…