Unauthenticated code execution via unchecked MCP commands
Published Aug 27, 2026 · Updated Aug 27, 2026
Command injection in GPT Researcher 0.14.7 and earlier allows remote attackers to execute code through the WebSocket endpoint. The WebSocket data path forwards attacker-controlled MCP command, argument, and environment fields to anyio.open_process without validation. Network access to the unauthenticated endpoint is sufficient for execution as the server process, although the maintainer treats this behavior as an intended capability for trusted operators.
Summary
What happened
Command injection in GPT Researcher 0.14.7 and earlier allows remote attackers to execute code through the WebSocket endpoint. The WebSocket data path forwards attacker-controlled MCP command, argument, and environment fields to anyio.open_process without validation. Network access to the unauthenticated endpoint is sufficient for execution as the server process, although the maintainer treats this behavior as an intended capability for trusted operators.
The record
- CVE
- CVE-2026-37006
- Published
- Aug 27, 2026
- Updated
- Aug 27, 2026
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-78, T1059
- Attack vector
- network
- Privileges
- unauthenticated
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?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
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
- WebSocket MCP command-execution proof of conceptfunctional · demonstrated
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