CVE-2026-42203: litellm — Fix

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.

Is your site exposed to CVE-2026-42203?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

8.8

HIGH

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

EPSS — Exploit Prediction

0.0006

Probability of exploitation

0.18%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-1336 CWE-1336

Affected Products

Vendor	Product	Versions
litellm	litellm	1.80.5 — 1.83.7

References

Advisories & Patches

https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862

Other References

https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable

Frequently Asked Questions

What is CVE-2026-42203? +

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. It has a CVSS v3.1 base score of 8.8 (HIGH).

How severe is CVE-2026-42203? +

CVE-2026-42203 has a CVSS v3.1 score of 8.8 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0006, placing it in the 0th percentile for exploitation probability.

What products are affected by CVE-2026-42203? +

CVE-2026-42203 affects products from litellm, specifically: litellm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2026-42203? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-34906

Server-Side Template Injection (SSTI) in Wirtualna Uczelnia allows an unauthenticated attacker to perform Remote Code Execution (RCE). In the endpoint …

CVE-2026-72717

Orval generates type-safe JavaScript clients in TypeScript from OpenAPI v3 and Swagger v2 specifications. Prior to 8.21.0, a ${...} expression …

CVE-2026-44129

SEPPmail Secure Email Gateway before version 15.0.4 contains a server-side template injection vulnerability in the new GINA UI because an …

CVE-2025-26789

An issue was discovered in Logpoint AgentX before 1.5.0. A vulnerability caused by limited access controls allowed li-admin users to …

CVE-2024-9150

Report generation functionality in Wyn Enterprise allows for code inclusion, but not sufficiently limits what code might be included. An …

CVE-2025-34300

A template injection vulnerability exists in Sawtooth Software’s Lighthouse Studio versions prior to 9.16.14 via the ciwweb.pl http://ciwweb.pl/ Perl web …

CVE-2026-42203