All vulnerabilities
CVE-2026-105148

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

SciPhi-AI R2R
Open in ThreatlineRecord JSON
CVSS
6.9Medium
ExploitationPublic exploit codeCISA's assessment says proof of concept code is public, assessed 5 Oct 2026. Not in the KEV catalogCISA via CVE List
Exploit odds (EPSS)0.28%Chance of exploitation activity in the next 30 days, higher than 19% of CVEs. Scored 23 Oct 2026FIRST EPSS
Fixed inNone listedNo source names a fixed version. Check the vendor advisory below
Published4 Oct 2026Updated 5 Oct 2026CVE List

What fixes it

No source in this snapshot names a fixed version. The vendor advisories under References are the place to check.

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.

Text from CVE List

Affected versions 7

  • R2Raffected: 3.6.0CVE List
  • R2Raffected: 3.6.1CVE List
  • R2Raffected: 3.6.2CVE List
  • R2Raffected: 3.6.3CVE List
  • R2Raffected: 3.6.4CVE List
  • R2Raffected: 3.6.5CVE List
  • R2Raffected: 3.6.6CVE List

References 5