Arbitrary command execution via auto-approved MCP configuration
Published Jun 27, 2025 · Updated Jul 3, 2025
Command injection in Roo Code before 3.20.3 allows remote attackers to execute arbitrary commands through a malicious agent prompt. With automatic project file writes enabled, the agent can write attacker-controlled commands into the workspace's .roo/mcp.json configuration, which MCP treats as executable. Exploitation requires prompt submission access, MCP enabled, and the non-default auto-approval of file writes, and successful commands run with the extension's privileges.
Summary
What happened
Command injection in Roo Code before 3.20.3 allows remote attackers to execute arbitrary commands through a malicious agent prompt. With automatic project file writes enabled, the agent can write attacker-controlled commands into the workspace's .roo/mcp.json configuration, which MCP treats as executable. Exploitation requires prompt submission access, MCP enabled, and the non-default auto-approval of file writes, and successful commands run with the extension's privileges.
The record
- CVE
- CVE-2025-53098
- Published
- Jun 27, 2025
- Updated
- Jul 3, 2025
- Vendor
- Roo Code, Inc.
- Product
- Roo Code
- Classifications
- CWE-77, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 27, 2025CVE publishedPublication date reported by the CVE source.
- Jul 3, 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=< 3.20.3
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