SSRF in Sciphi-Ai R2r
CVE-2026-105148
A vulnerability was identified in SciPhi-AI R2R up to 3.6.6. This vulnerability affects unknown code of the file py/shared/abstractions/llm.py of the component Retrieval Completion API Endpoint. Such manipulation of the argument generation_config.api_base leads to server-side request forgery. The attack can be launched remotely. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.
Vulnerability class: SSRF (Server-Side Request Forgery)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.3 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Sciphi-Ai R2r — versions 3.6.0, 3.6.1, 3.6.2
Weakness classification (CWE)
References
- vuldb.com/vuln/413373 (technical-description, vdb-entry)
- vuldb.com/vuln/413373/cti (signature, permissions-required)
- vuldb.com/cve/CVE-2026-105148 (third-party-advisory)
- vuldb.com/submit/947817 (third-party-advisory)
- gist.github.com/DReazer/6c1fd0ef98900fbbfa383faa20f731f6 (exploit)
Frequently asked questions
- What is CVE-2026-105148?
- CVE-2026-105148 is a high-severity vulnerability in Sciphi-Ai R2r, classified under Server-Side Request Forgery (SSRF). CVSS score: 7.3/10. Published 2026-10-04.
- How severe is CVE-2026-105148?
- High severity. CVSS v3 base score is 7.3 out of 10.