CVE-2026-105148 SciPhi-AI R2R Retrieval Completion API Endpoint llm.py server-side request forgery
Remote attackers can exploit server-side request forgery in the R2R Retrieval Completion API to access internal resources or bypass security controls.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-105148?
CVE-2026-105148 is a medium-severity server-side request forgery vulnerability in SciPhi-AI R2R, published on 4 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-918
Which versions are affected by CVE-2026-105148?
How do I fix CVE-2026-105148?
No fix has been published for CVE-2026-105148 yet. Limit exposure of the affected software until one is available.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2026-105148 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-105148 exists.
Sources
Also known as GHSA-2j4q-255p-4658.