Security readout for executives and security teams
Plain-English summary
GPT Researcher deployments running version 0.14.7 or earlier may let an unauthenticated internet attacker execute code through the WebSocket interface using malicious Model Context Protocol configurations. Successful compromise could expose data, alter systems, or disrupt service. The supplied sources do not identify a fixed release.
Executive priority
Treat this as an immediate remediation priority for internet-facing or otherwise untrusted-access deployments. Establish exposure today, restrict reachable WebSocket endpoints, and seek authoritative upgrade guidance. Internal, isolated instances remain important because compromise could affect all three core security objectives.
Technical view
CVE-2026-37006 is an improper-authentication vulnerability, classified as CWE-287, in the gpt-researcher WebSocket endpoint. Crafted MCP configuration input can reportedly reach code execution without credentials or user interaction. CVSS 3.1 rates it 9.8: network-accessible, low complexity, and high confidentiality, integrity, and availability impact.
Likely exposure
Exposure is most likely where gpt-researcher 0.14.7 or earlier is deployed and its WebSocket endpoint is reachable by untrusted networks. The supplied CVE data lacks CPEs, deployment details, and a definitive affected-version table, so organizations must confirm their own installations and access paths.
Exploitation context
The vulnerability is described as remotely exploitable without authentication, privileges, or user interaction. However, it is not listed as KEV in the supplied bundle, and the provided sources do not establish active exploitation, public exploit availability, or observed attacks.
Researcher notes
The record supplies a precise product version in its narrative but lists vendor, product, versions, and CPE data as unavailable. No fixed version, patch, exploitation telemetry, or technical root-cause detail is included. Validation should remain non-destructive and focus on version, reachability, authentication enforcement, and relevant telemetry.
Mitigation direction
- Inventory gpt-researcher deployments and prioritize systems running version 0.14.7 or earlier.
- Restrict WebSocket access to trusted networks or authenticated gateways while remediation is evaluated.
- Review vendor or project guidance for a confirmed fixed release; none is identified in the supplied sources.
- Disable unnecessary MCP configuration functionality where operationally safe.
- Monitor exposed systems for suspicious WebSocket and MCP-related activity.
Validation and detection
- Confirm installed gpt-researcher versions from deployment records and package inventories.
- Determine whether each WebSocket endpoint is reachable without authentication from untrusted networks.
- Review gateway, application, and host logs for unexpected WebSocket connections or MCP configurations.
- Verify temporary network restrictions block untrusted access without disrupting authorized workflows.
- After updating, confirm the installed release matches authoritative project guidance and repeat exposure checks.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-287: Credential and account abuse lookup
Authentication and credential weaknesses can make valid-account abuse and credential telemetry useful review starting points. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-37006 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.8 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9CISA-ADPVulnerability scoring details
Base CVSS 3.1 score
9.8CriticalVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://yerangamage.com/cves/detail/?slug=gptresearcher-websocket-rceCVE reference, mitre
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE mapping pending import
This CVE carries a CWE mapping that will resolve to a full Glexia CWE intelligence page after the official CWE import is complete.