PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.
← Back | CVE Intelligence Hub

CVE-2026-55607[High]

Curated 1 security research writeups, vulnerability advisories and exploitation analyses for CVE-2026-55607.

Vendor
Anthropic
Product
Claude Code
Affected versions
< 2.1.163
CVSS
7.7
Coverage Span
2026-06-26
Reports
1 related reports

Associated Reports & Timeline

1.
Claude Code: Unsandboxed Code Execution from Prompt Injection via Git Worktree Path Confusion (CVE-2026-55607)
github.com | vulnerability | High | | Original ↗ | .md | #ai-security | #bug-bounty | #rce
Anthropic patched a high-severity sandbox escape vulnerability (CVE-2026-55607, CVSS 7.7) in Claude Code CLI prior to version 2.1.163. Security researcher Metnew demonstrated how prompt injection via CLAUDE.md can manipulate Claude Code's git worktree tools to induce gitdir confusion. By leveraging Git's core.fsmonitor hook and directory symlinks to $HOME, the exploit overwrites ~/.zshenv, achieving unsandboxed code execution outside macOS seatbelt restrictions.
Why it matters: This research highlights how AI coding agent tools expand the attack surface, demonstrating that prompt injection chained with git filesystem primitives can compromise host environments before process sandbox boundaries initialize.