Unauthenticated code execution via unvalidated MCP commands
Published Apr 6, 2026 · Updated Apr 6, 2026
Code injection in GPT Researcher 3.4.0 through 3.4.3 allows remote attackers to execute commands through the unauthenticated /ws endpoint. extract_command_data accepts client-supplied MCP command, argument, and environment fields that flow without validation to anyio.open_process. Any network client that can reach the WebSocket service can run a process with the GPT Researcher server account's privileges.
Summary
What happened
Code injection in GPT Researcher 3.4.0 through 3.4.3 allows remote attackers to execute commands through the unauthenticated /ws endpoint. extract_command_data accepts client-supplied MCP command, argument, and environment fields that flow without validation to anyio.open_process. Any network client that can reach the WebSocket service can run a process with the GPT Researcher server account's privileges.
The record
- CVE
- CVE-2026-5631
- Published
- Apr 6, 2026
- Updated
- Apr 6, 2026
- Vendor
- Assaf Elovic
- Product
- GPT Researcher
- Classifications
- CWE-74, CWE-94, T1059.004, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 6, 2026CVE publishedPublication date reported by the CVE source.
- Apr 6, 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=3.4.0
- Affected versionversion=3.4.1
- Affected versionversion=3.4.2
- Affected versionversion=3.4.3
What conditions does exploitation require?
What is affected?
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
- WebSocket MCP command-injection proof of conceptfunctional · demonstrated
- Metasploit command-injection moduleweaponized · 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