Browse / Indirect Prompt Injection / CVE-2025-54794
Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access
- 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
- 1.5% chance of exploitation in 30 days
How it works, in short
A prefix-based directory check accepts a sibling directory named like the working directory, so untrusted context content can steer reads outside the project. (Our summary, written by a model. The source text is below.)
Details
Due to a path validation flaw using prefix matching instead of canonical path comparison, it was possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of (or ability to create) a directory with the same prefix as the CWD and the ability to add untrusted content into a Claude Code context window.
Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.
Thank you to Elad Beber (Cymulate) for reporting this issue!
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-pmw4-pwvc-3hx2
- https://nvd.nist.gov/vuln/detail/CVE-2025-54794
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.