Read the docs
TI-2026-30524 Aliases CVE-2026-42203GHSA-xqmj-j6mv-4862

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

Priority LOW 39CWE-1336Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
Code execution
Confidentiality · integrity · availability
High · High · None
Fix status
Partial Red Hat: 1 without a fix

Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-1336.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00373 31st percentileScored 2026-11-07
Fix Partial litellm (BerriAI): 1.83.7litellm (PyPI): 1.83.7Red Hat: 1 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
BerriAIlitellm1.80.5 to before 1.83.71.83.7Patch availableCNA
—litellm (PyPI)1.80.5 to before 1.83.71.83.7Patch availableGHSA-xqmj-j6mv-4862
  • litellm VendorBerriAI Affected 1.80.5 to before 1.83.7 Fixed in 1.83.7 Patch available CNA
  • litellm (PyPI) Vendor— Affected 1.80.5 to before 1.83.7 Fixed in 1.83.7 Patch available GHSA-xqmj-j6mv-4862

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*1.80.5 to before 1.83.7VulnerableBerriAI
  • cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* Versions 1.80.5 to before 1.83.7 Vulnerable ·BerriAI

Remediation

  • Fix · CNA litellm (BerriAI) Fixed in 1.83.7
  • Fix · GHSA-xqmj-j6mv-4862 litellm (PyPI) Fixed in 1.83.7 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat Ansible Automation Platform 2AffectedNo fix yet
Not affected: 2 products
  • Exploit Intelligence
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-42203
  2. 2026-10-03 Alias added: GHSA-xqmj-j6mv-4862
  3. 2026-10-05 EPSS moved to the 50th–90th percentile
  4. 2026-10-25 EPSS moved to the below the 50th percentile
  5. 2026-10-25 Priority changed: MEDIUM → LOW

References

Patch 1

Advisory 1

Other 2

  • TI-2026-26015 Trivy ecosystem supply chain briefly compromised KEVCVSS 4.0CRITICAL 9.4
  • TI-2026-30529 LiteLLM: SQL injection in Proxy API key verification KEVCVSS 4.0CRITICAL 9.3
  • TI-2026-30582 LiteLLM: Authenticated command execution via MCP stdio test endpoints KEVCVSS 4.0HIGH 8.7
  • TI-2026-42639 LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback KEVCVSS 4.0HIGH 8.8
  • TI-2024-05340 Remote Code Execution in BerriAI/litellm CVSS 3.1CRITICAL 9.8
  • TI-2024-02760 Server-Side Template Injection in BerriAI/litellm CVSS 3.0CRITICAL 9.8
See all 36 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences