peter bassill · operator
$ cve CVE-2026-42208 JSON

CVE-2026-42208 KEV

9.8
CRITICAL · CVSS 3.1 · EPSS 5.8% (pctl 93)

Patch first

On CISA KEV — known exploited in the wild, due 2026-05-11.

Description

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.

Scoring

CVSS9.8 (CRITICAL, v3.1)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS5.77% — more likely to be exploited than 93% of all CVEs
WeaknessCWE-89
On CISA KEVyes — remediate by 2026-05-11
Public exploitnone known
Published2026-05-08
Last modified2026-07-15

CISA KEV

NameBerriAI LiteLLM SQL Injection Vulnerability
Added2026-05-08
Due2026-05-11
Vendor / productBerriAI / LiteLLM
Ransomware usenone reported

Affected (1)

VendorProduct
litellmlitellm

References

→ the Explorer  ·  watch your stack  ·  NVD