Browse / Tool and Agent Misuse / CVE-2026-25725
Claude Code has Sandbox Escape via Persistent Configuration Injection in settings.json
- Class
- Tool and Agent Misuse (filed by a model that read the advisory)
- Technique
- Sandbox escape
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Sandbox or allowlist
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- EPSS
- 0.5% chance of exploitation in 30 days
How it works, in short
Sandboxed code could create a missing settings.json and add startup hooks that run on the host after restart. (Our summary, written by a model. The source text is below.)
Details
Claude Code's bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did not exist at startup. While the parent directory was mounted as writable and .claude/settings.local.json was explicitly protected with read-only constraints, settings.json was not protected if it was missing. This allowed malicious code running inside the sandbox to create this file and inject persistent hooks (such as SessionStart commands) that would execute with host privileges when Claude Code was restarted.
Users on standard Claude Code auto-update received this fix automatically. Users performing manual updates are advised to update to the latest version.
Claude Code thanks hackerone.com/edbr for reporting this issue!
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-ff64-7w26-62rf
- https://nvd.nist.gov/vuln/detail/CVE-2026-25725
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.