CONTENTUM.COMA specialist. A plan. A result.

Exploited vulnerabilities · BerriAI

CVE-2026-59822
BerriAI LiteLLM Improper Authentication Vulnerability

BerriAI LiteLLM contains an improper authentication vulnerability in the MCP Streamable HTTP endpoint that could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.

Description in the NVD

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

Required action according to CISA

Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.

What to do now

  • Check your exposureFind out whether BerriAI LiteLLM runs anywhere in your environment, including systems of suppliers.
  • Patch or mitigateApply the vendor update. If that is not possible at once, use the vendor's mitigation or take the system off the network.
  • Look for signs of an attackThis vulnerability is exploited in real attacks. Review the logs of affected systems for the time before the patch.

References

More exploited vulnerabilities in BerriAI products

Data: CISA Known Exploited Vulnerabilities Catalog and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.