CVE-2026-105148: medium-severity vulnerability in SciPhi-AI R2R
SciPhi-AI R2R Retrieval Completion API Endpoint llm.py server-side request forgery
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
33Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 6.9epss 0.3%
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Affected products
SciPhi-AI · R2Rpublic PoCs found — 1
cve_referencegist.github.com/DReazer/6c1fd0ef98900fbbfa383faa20f731f6unverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
Related CVEs — SciPhi-AI R2R
In the same product, most dangerous first.
CVE-2026-82526CRITICALR2R 3.6.6 SQL Injection via Vector Index Creation EndpointEPSS 0.7%CVE-2026-82527HIGHR2R 3.6.6 SQL Injection via Retrieval Search Filter KeyEPSS 0.5%CVE-2026-82271HIGHR2R Missing Ownership Check Allows Modifying Other Users' ConversationsEPSS 0.4%CVE-2026-105147MEDIUMSciPhi-AI R2R JWT Secret hard-coded credentialsEPSS 0.3%