Which versions of Gpt Researcher are affected by CVE-2026-5633?

gpt-researcher versions up to 3.4.3 contain an unauthenticated server-side request forgery vulnerability that allows remote attackers to manipulate data sources, potentially compromising…

Is there a public PoC exploit available for CVE-2026-5633?

Yes, a public proof-of-concept exploit is available for CVE-2026-5633. Prioritise patching immediately. EPSS: 0.0%.

How to fix or mitigate CVE-2026-5633?

Within 24 hours: identify all gpt-researcher deployments in production and air-gap or restrict network access to the ws endpoint pending further assessment. Within 7 days: implement WAF rules blocking suspicious source_urls parameters, isolate affected instances to trusted networks only, and contact gpt-researcher maintainers for status on patch timeline. Within 30 days: evaluate migration to alternative research tools, upgrade to patched version if released, or implement mandatory authentication and request validation layers in front of the ws endpoint.

Gpt Researcher CVE-2026-5633

Q: What is the CVSS score of CVE-2026-5633?

CVE-2026-5633 has a CVSS 4.0 base score of 5.5 (Medium). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.0%.

EUVD-2026-19190 MEDIUM

Server-Side Request Forgery (SSRF) (CWE-918)

2026-04-06 VulDB

GHSA-8p84-j4x4-c993

SSRF Gpt Researcher Assafelovic

5.5

CVSS 4.0 · Vendor: VulDB

Severity by source

Vendor (VulDB) PRIMARY

5.5 MEDIUM

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Primary rating from Vendor (VulDB) · only source for this CVE.

CVSS VectorVendor: VulDB

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Lifecycle Timeline

CVSS changed

Apr 29, 2026 - 01:11 NVD

6.9 (MEDIUM) 5.5 (MEDIUM)

PoC Detected

Apr 07, 2026 - 13:20 vuln.today

Public exploit code

EUVD ID Assigned

Apr 06, 2026 - 07:45 euvd

EUVD-2026-19190

Analysis Generated

Apr 06, 2026 - 07:45 vuln.today

CVE Published

Apr 06, 2026 - 07:00 nvd

MEDIUM 6.9

DescriptionCVE.org

A vulnerability was determined in assafelovic gpt-researcher up to 3.4.3. Affected is an unknown function of the component ws Endpoint. Executing a manipulation of the argument source_urls can lead to server-side request forgery. It is possible to launch the attack remotely. The exploit has been publicly disclosed and may be utilized. The project was informed of the problem early through an issue report but has not responded yet.

AnalysisAI

Server-side request forgery in gpt-researcher versions up to 3.4.3 allows unauthenticated remote attackers to manipulate the source_urls parameter at the ws endpoint, enabling partial confidentiality, integrity, and availability impacts. A publicly available exploit exists via GitHub issue #1696, though the vendor has not responded to early disclosure. EPSS data not provided, but the low attack complexity (AC:L) and proof-of-concept availability elevate immediate risk for exposed instances.

Technical ContextAI

This is a classic server-side request forgery (CWE-918) vulnerability in the gpt-researcher project, an open-source autonomous research agent framework. The flaw resides in the WebSocket (ws) endpoint's handling of the source_urls argument. SSRF occurs when an application accepts user-controlled URLs and fetches them server-side without proper validation. Attackers can force the server to make requests to arbitrary internal or external resources, bypassing network segmentation, accessing cloud metadata services (e.g., AWS IMDSv1 at 169.254.169.254), or scanning internal networks. The CPE identifier confirms affected product as assafelovic:gpt-researcher through version 3.4.3. The CVSS vector (AV:N/AC:L/PR:N/UI:N) indicates this is a network-accessible vulnerability requiring no authentication or user interaction, making exploitation straightforward for remote attackers who can reach the ws endpoint.

RemediationAI

Upgrade to a patched version once available; monitor the official GitHub repository at https://github.com/assafelovic/gpt-researcher/ for security updates, though vendor has not responded to disclosure at time of analysis. Until a patch is released, implement compensating controls: restrict network access to the ws endpoint using firewall rules or reverse proxy ACLs to allow only trusted clients; deploy web application firewall rules to validate and sanitize source_urls parameters, rejecting private IP ranges (RFC 1918), localhost addresses, cloud metadata endpoints (169.254.169.254, fd00:ec2::254), and non-HTTP/HTTPS schemes; implement egress filtering to prevent the server from initiating connections to internal resources or cloud metadata services; consider disabling the vulnerable ws endpoint entirely if not required for operations. Review server logs for suspicious source_urls parameter values or unexpected outbound connections as indicators of exploitation attempts. Refer to the vulnerability disclosure at https://github.com/assafelovic/gpt-researcher/issues/1696 for technical details and community-proposed mitigations, and monitor VulDB entries at https://vuldb.com/vuln/355421 for updates.