Browse / Indirect Prompt Injection / CVE-2026-39861
Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace
- Class
- Indirect Prompt Injection (filed by a model that read the advisory)
- Technique
- Sandbox escape
- Also involves
- Tool and Agent Misuse
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Sandbox or allowlist
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- EPSS
- 0.7% chance of exploitation in 30 days
How it works, in short
A sandboxed process creates symlinks to outside locations and the unsandboxed process later writes through them, with untrusted content in context able to trigger this. (Our summary, written by a model. The source text is below.)
Details
Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the symlink and wrote to the target location outside the workspace without prompting the user for confirmation. This allowed a sandbox escape where neither the sandboxed command nor the unsandboxed app could independently write outside the workspace, but their combination could write to arbitrary locations, potentially leading to code execution outside the sandbox. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window to trigger sandboxed code execution via prompt injection.
Users on standard Claude Code auto-update have received this fix automatically. Users performing manual updates are advised to update to the latest version.
Claude Code thanks hackerone.com/philts for reporting this issue.
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-vp62-r36r-9xqp
- https://nvd.nist.gov/vuln/detail/CVE-2026-39861
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.