Code execution via unprotected VS Code settings
Published Jul 7, 2025 · Updated Jul 8, 2025
Code execution in Roo Code before 3.22.6 allows remote attackers to run arbitrary commands through agent-authored VS Code settings. The write tool treated .vscode/settings.json as an ordinary auto-approved target, allowing php.validate.executablePath to reference an arbitrary command that runs when a PHP file triggers validation. Exploitation requires influence over an agent prompt and auto-approved file writes, which are disabled by default; successful commands run with the editor user's privileges.
Summary
What happened
Code execution in Roo Code before 3.22.6 allows remote attackers to run arbitrary commands through agent-authored VS Code settings. The write tool treated .vscode/settings.json as an ordinary auto-approved target, allowing php.validate.executablePath to reference an arbitrary command that runs when a PHP file triggers validation. Exploitation requires influence over an agent prompt and auto-approved file writes, which are disabled by default; successful commands run with the editor user's privileges.
The record
- CVE
- CVE-2025-53536
- Published
- Jul 7, 2025
- Updated
- Jul 8, 2025
- Vendor
- Roo Code, Inc.
- Product
- Roo Code
- Classifications
- CWE-552, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 7, 2025CVE publishedPublication date reported by the CVE source.
- Jul 8, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 3.22.6
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo