# CVE-2026-5625: assafelovic gpt-researcher XSS in WebSocket Interface

Source: https://junglewise.ai/threats/cve-2026-5625-assafelovic-gpt-researcher-xss-in-websocket-interface  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-04-06. Updated: 2026-07-24  
License: CC BY 4.0 with a link back

CVE-2026-5625 · Severity: medium · CVSS 4.3 · Published 2026-04-06

gpt-researcher is an autonomous AI agent used to conduct deep research on various topics. A security vulnerability in its WebSocket interface allows an attacker to inject malicious scripts by manipulating the 'task' argument. If a user is tricked into interacting with a malicious task, it could lead to unauthorized actions being performed in their browser session, potentially compromising sensitive research data or user accounts.

Technologies: [Assaf Elovic GPT Researcher](https://junglewise.ai/threats/technologies/gpt-researcher). Vendors: [Assaf Elovic](https://junglewise.ai/threats/vendors/assaf-elovic).

## Quick answers

**Is CVE-2026-5625 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-5625 being exploited in the wild.

**How severe is CVE-2026-5625?** Medium severity, with a CVSS score of 4.3, published 6 April 2026.

**Which products and versions are affected?** Assaf Elovic GPT Researcher up to 3.4.3.

**Is there a fix for CVE-2026-5625?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-5625 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-5625?** Check whether you run Assaf Elovic GPT Researcher at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A reflected cross-site scripting (XSS) vulnerability exists in gpt-researcher versions up to 3.4.3. The flaw is located in the WebSocket interface within the gpt_researcher/skills/researcher.py file, where the 'task' argument is processed without sufficient input sanitization. A remote attacker can exploit this by crafting a malicious task name containing script tags, which are then executed in the context of the victim's browser. This requires user interaction, typically via a social engineering vector. As of the advisory date, the project has been notified but a formal patch has not been confirmed.

## Affected products

- assafelovic gpt-researcher up to 3.4.3

## Timeline

- 2026-04-06: disclosed: Public disclosure via VulDB and NVD
- 2026-04-06: advisory

## References

- [https://github.com/assafelovic/gpt-researcher/](https://github.com/assafelovic/gpt-researcher/)
- [https://github.com/assafelovic/gpt-researcher/issues/1692](https://github.com/assafelovic/gpt-researcher/issues/1692)
- [https://vuldb.com/submit/785832](https://vuldb.com/submit/785832)
- [https://vuldb.com/vuln/355415](https://vuldb.com/vuln/355415)
- [https://vuldb.com/vuln/355415/cti](https://vuldb.com/vuln/355415/cti)

## Related threats

- [assafelovic GPT Researcher command injection in MCP STDIO](https://junglewise.ai/threats/cve-2025-65720-assafelovic-gpt-researcher-command-injection-in-mcp-stdio)
- [assafelovic gpt-researcher SSRF in ws Endpoint](https://junglewise.ai/threats/cve-2026-5633-assafelovic-gpt-researcher-ssrf-in-ws-endpoint)
- [assafelovic gpt-researcher missing authentication in REST API and WebSockets](https://junglewise.ai/threats/cve-2026-5632-assafelovic-gpt-researcher-missing-authentication-in-rest-api-and)
- [assafelovic gpt-researcher RCE in WebSocket endpoint](https://junglewise.ai/threats/cve-2026-5631-assafelovic-gpt-researcher-rce-in-websocket-endpoint)
- [assafelovic gpt-researcher XSS in Report API](https://junglewise.ai/threats/cve-2026-5630-assafelovic-gpt-researcher-xss-in-report-api)