Browse / Indirect Prompt Injection / CVE-2025-66032
Claude Code Command Validation Bypass Allows Arbitrary Code Execution
- Class
- Indirect Prompt Injection (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Tool and Agent Misuse
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Approval or confirmation prompt
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- EPSS
- 0.7% chance of exploitation in 30 days
How it works, in short
Shell parsing errors around $IFS and short flags let commands pass read-only checks, so injected context content can run arbitrary commands without approval. (Our summary, written by a model. The source text is below.)
Details
Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires 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.
Thank you to [RyotaK](hxxps://ryotak.net) from [GMO Flatt Security Inc.](hxxps://flatt.tech/en/) for reporting this issue!
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3
- https://nvd.nist.gov/vuln/detail/CVE-2025-66032
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.