Code execution via untrusted MCP server instructions
Published Aug 27, 2026 · Updated Aug 27, 2026
Code injection in Roo Code 3.51.0 through 3.51.1 allows remote authenticated users to execute code through a malicious MCP server. The fetch_instructions function in malicious_mcp_server.py supplies attacker-controlled MCP instructions that enter the model context without neutralization. A user must configure and interact with the malicious server; the injected instructions can invoke tools with the editor user's privileges.
Summary
What happened
Code injection in Roo Code 3.51.0 through 3.51.1 allows remote authenticated users to execute code through a malicious MCP server. The fetch_instructions function in malicious_mcp_server.py supplies attacker-controlled MCP instructions that enter the model context without neutralization. A user must configure and interact with the malicious server; the injected instructions can invoke tools with the editor user's privileges.
The record
- CVE
- CVE-2026-81835
- Published
- Aug 27, 2026
- Updated
- Aug 27, 2026
- Vendor
- Roo Code, Inc.
- Product
- Roo Code
- Classifications
- CWE-94, CWE-74, T1204
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 27, 2026CVE publishedPublication date reported by the CVE source.
- Aug 27, 2026Record 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=3.51.0
- Affected versionversion=3.51.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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
- Malicious MCP server proof of conceptproof of concept · unverified
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