CVE-2026-42203
LiteLLM: Server-Side Template Injection in /prompts/test endpoint
HIGH 8.6EPSS 0.7%
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.
- Affected
- BerriAI · litellm
- CVSS v4.0 GITHUB
- 8.6 HIGH
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS v4.0 GitHub
- 8.6 HIGH
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N - CVSS v3.1 NVD
- 8.8 HIGH
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - EPSS
- 0.66% chance of exploitation in the next 30 days, 51st percentile
- Published
- 2026-05-08
- Updated
- 2026-07-15
Proof-of-concept exploits (1)
- Astianjy/CVE-2026-422030★ · 2026-05-15
Security advisories
- BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862
- advisories/GHSA-xqmj-j6mv-4862
- BerriAI/litellm/releases/tag/v1.83.7-stable