Paper/Archive/CVE-2026-42208

CVE-2026-42208

BerriAI litellm — LiteLLM: SQL injection in Proxy API key verification

KEV · due 11 May EPSS 89%public exploit SSVC act CVSS 9.8

CVSS 9.8 (CNA, NVD agree)9.8 / 10 × 3029.4 In CISA KEV+3030.0 EPSS percentile 99.8.998 × 2020.0 Exploit: SSVC active+1010.0 SSVC exploitation: active+1010.0

Description · from the CVE record

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.

Affected

ProductAffectedFixed inSource

litellm>= 1.81.16, < 1.83.7–CNA

Lightspeed Coresee advisory–redhat-SADP

Red Hat Ansible Automation Platform 2see advisory–redhat-SADP

Red Hat OpenShift AI (RHOAI)see advisory–redhat-SADP

Scores by source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

redhat-SADP (CNA)9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

GitHub_M (CNA)9.3CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CISA ADPSSVCExploitation: active · Automatable: yes · Technical impact: total

References

refgithub.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc refgithub.com/BerriAI/litellm/releases/tag/v1.83.7-stable refcisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208 refaccess.redhat.com/security/cve/CVE-2026-42208 refbugzilla.redhat.com/show_bug.cgi?id=2463965 refsecurity.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json kevcisa.gov/known-exploited-vulnerabilities-catalog