RCE in Assafelovic Gpt-Researcher
CVE-2026-5625
A weakness has been identified in assafelovic gpt-researcher up to 3.4.3. This issue affects some unknown processing of the file gpt_researcher/skills/researcher.py of the component WebSocket Interface. Executing a manipulation of the argument task can lead to cross site scripting. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
Vulnerability class: XSS (Cross-Site Scripting)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 4.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N.
EPSS exploit prediction
EPSS: 0.004 (36.7th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 37th percentile — 36.7% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.004 · change: +0.002
Affected products
- Assafelovic Gpt-Researcher — versions 3.4.0, 3.4.1, 3.4.2
Weakness classification (CWE)
References
- vuldb.com/vuln/355415 (technical-description, vdb-entry)
- vuldb.com/vuln/355415/cti (signature, permissions-required)
- vuldb.com/submit/785832 (third-party-advisory)
- github.com/assafelovic/gpt-researcher/issues/1692 (issue-tracking, exploit)
- github.com/assafelovic/gpt-researcher/ (product)
Frequently asked questions
- What is CVE-2026-5625?
- CVE-2026-5625 is a medium-severity vulnerability in Assafelovic Gpt-Researcher, classified under Cross-site Scripting. CVSS score: 4.3/10. Published 2026-04-06.
- How severe is CVE-2026-5625?
- Medium severity. CVSS v3 base score is 4.3 out of 10.