How severe is CVE-2026-59822?

No CVSS score has been assigned to CVE-2026-59822 yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by CVE-2026-59822?

CVE-2026-59822 affects the following packages: litellm (PyPI). Ecosystems affected: PyPI.

How do I fix CVE-2026-59822?

Update litellm to 1.84.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-59822 is resolved across your whole dependency graph.

How do I detect CVE-2026-59822 in my PyPI dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for litellm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate CVE-2026-59822 if there is no patch (or I can't update yet)?

Put an independent control in front of the weakness: restrict the affected endpoint or interface to trusted networks, require an additional authentication factor or proxy-level check, and invalidate existing sessions and credentials in case the flaw has already been used.

Is CVE-2026-59822 actively exploited in the wild?

No public exploit code has been indexed for CVE-2026-59822 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2026-59822?

CVE-2026-59822 has an EPSS (Exploit Prediction Scoring System) score of 0.8%, placing it in the 56th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

Is CVE-2026-59822 in the CISA Known Exploited Vulnerabilities catalog?

Yes. CVE-2026-59822 (BerriAI LiteLLM Improper Authentication Vulnerability) was added to CISA's Known Exploited Vulnerabilities (KEV) catalog on 2026-09-02. CISA required all US federal civilian agencies to remediate this vulnerability by 2026-09-16. The required action was: 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. Being listed in the KEV catalog is the strongest possible confirmation of active exploitation — treat this as a critical priority.

What type of vulnerability is CVE-2026-59822?

CVE-2026-59822 is classified as Improper Authentication (CWE-287), Missing Authentication (CWE-306). These weakness types describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was CVE-2026-59822 published, and has it been updated?

CVE-2026-59822 was published on July 8, 2026 and was last updated on September 5, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍 PyPI

CISA KEV · ACTIVELY EXPLOITED

CVE-2026-59822 — litellm

Fix: BerriAI/litellm@73869f0

CVE-2026-59822 is a Improper Authentication vulnerability in litellm. It is in CISA's Known Exploited Vulnerabilities catalog (added 2026-09-02) — treat it as actively exploited and patch now. A fix is available for litellm — see the affected versions and patch details below.

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

Also known asGHSA-7488-6r32-c95qPYSEC-2026-3479

Published

Jul 8, 2026

Updated

Sep 5, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Oct 7, 2026 · OSV.dev, NVD, CISA KEV, FIRST.org (EPSS)

Exploitation Status

Actively exploited in the wild

Confirmed by CISA's Known Exploited Vulnerabilities catalog on 2026-09-02. Federal agencies were required to remediate by 2026-09-16.
CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.

Exploitation and automatability from CISA (KEV catalog and SSVC triage) for CVE-2026-59822.

EPSS Exploitation Probability

via FIRST.org ↗

0.8%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs56th percentile — riskier than 56% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

🐍litellm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Impact

LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.

The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty UserAPIKeyAuth() object. This allowed requests with a fabricated Authorization header to reach MCP tooling without a valid LiteLLM key.

An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP.

Patches

The issue is fixed in 1.84.0.

We recommend upgrading to 1.84.0 or later.

Workarounds

If upgrading is not immediately possible, disable MCP routes or block access to /mcp/ and related MCP endpoints at your reverse proxy or API gateway.

References

v1.84.0

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`litellm`	all versions	1.84.0`pip install --upgrade 'litellm==1.84.0'`

Affected Products

1 product · 1 configurations

Application

litellmlitellm

< 1.84.0

range

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for litellm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update litellm to 1.84.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-59822 is resolved across your whole dependency graph.
Workarounds
Put an independent control in front of the weakness: restrict the affected endpoint or interface to trusted networks, require an additional authentication factor or proxy-level check, and invalidate existing sessions and credentials in case the flaw has already been used.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatImportant

affects LiteLLM proxy deployments prior to 1.84.0 where the MCP Streamable HTTP endpoint is exposed. Red Hat products that include LiteLLM as a Python dependency— including Red Hat OpenShift AI (odh-mlflow-rhel9 and similar images), Red Hat Ansible Automation Platform Lightspeed chatbot images…

Workaround published by Red Hat

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

Source: Red Hat security advisory for CVE-2026-59822 (CC BY 4.0)

Frequently Asked Questions

### Impact LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token. The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty `UserAPIKeyAuth()` object. This allowed requests with a fabricated `Authorization` header to reach MCP tooling without a valid LiteLLM key. An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP. ### Patches The is