CVE-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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
litellmPyPI | >= 1.80.5, < 1.83.7 | 1.83.7 |
Affected products
3- osv-coords2 versions
< 1.83.10.0-r0+ 1 more
- (no CPE)range: < 1.83.10.0-r0
- (no CPE)range: >= 1.80.5, < 1.83.7
Patches
Vulnerability mechanics
References
4- github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862nvdMitigationPatchVendor AdvisoryWEB
- github.com/advisories/GHSA-xqmj-j6mv-4862ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-42203ghsaADVISORY
- github.com/BerriAI/litellm/releases/tag/v1.83.7-stablenvdProductRelease NotesWEB
News mentions
0No linked articles in our index yet.