CVE-2026-42203HIGH 8.8EPSS p22.8%

CVE-2026-42203CVE-2026-42203

Description

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.

Scoring

CVSS 3.18.8 (HIGH)
VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS0.31% probability of exploitation · percentile 22.8% · 2026-06-18T12:00:27Z
Published2026-05-08
Last modified2026-05-13

Underlying weaknesses· 1

CWE-1336

References

  1. https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable
  2. https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862

1

TypeTargetConfidenceTier
WeaknessImproper Neutralization of Special Elements Used in a Template Enginecwe-13360%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
BerriAI LiteLLM Command Injection Vulnerability
CVE
CVE-2026-35029
CVE
CVE-2026-47101
CVE
CVE-2026-47102
CVE
CVE-2026-35030
CVE
CVE-2026-40217
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.