Log in Start free

Vulnerability · Published Oct 4, 2026 · Assigned by VulDB

CVE-2026-105148SciPhi-AI R2R Retrieval Completion API Endpoint llm.py server-side request forgery

High 7.3

In plain English

A high-severity server-side request forgery in R2R from SciPhi-AI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 20% of all known vulnerabilities).

Severity (CVSS 3.1)7.3High
Exploit odds (30 days)0.3%top 79.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

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.

Affected products (as reported)

VendorProductVersions
SciPhi-AI R2R 3.6.03.6.13.6.23.6.33.6.43.6.53.6.6

Weakness: CWE-918 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:C

References