Browse / Indirect Prompt Injection / CVE-2026-24053
Claude Code has a Path Restriction Bypass via ZSH Clobber which Allows Arbitrary File Writes
- Class
- Indirect Prompt Injection (filed by a model that read the advisory)
- Technique
- Path traversal and file access
- Also involves
- Tool and Agent Misuse
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Path restriction
- 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
Command validation misparses zsh clobber redirection, so injected content can make the agent write files outside the working directory without a permission prompt. (Our summary, written by a model. The source text is below.)
Details
Due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the user to use ZSH and the ability to add untrusted content into a Claude Code context window.
Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.
Claude Code thanks https://hackerone.com/alexbernier for reporting this issue!
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-q728-gf8j-w49r
- https://nvd.nist.gov/vuln/detail/CVE-2026-24053
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.