CriticalCVE-2026-114612

    litellm: Improper Privilege Management (CVE-2026-114612)

    Published Sources: BSI

    What is affected, what to do

    Update LiteLLM to version 1.100.4, litellm to version 1.101.3.

    Affected
    • BerriAI LiteLLM gte 1.87.0, < 1.100.4..*

    Not sure whether and how you are affected? Ask a question about this vulnerability

    Metrics

    9.9

    Priority

    XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

    Source: Vendor (CNA), CVSS v3

    9.9

    CVSS v3

    Severity Critical on the scale from 0 to 10.

    Source: BSI

    0.3 %

    EPSS score

    Low — model estimates < 1% exploitation likelihood.

    Source: FIRST EPSS, percentile 24.7

    Show all metrics
    Severity
    Critical
    Priority (0–325)

    The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first?

    Read in glossary
    84.36 Methodology
    Exploit maturity

    An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack.

    Read in glossary
    no public PoC known
    XIEM Effective CVSS

    XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command.

    Read in glossary
    9.9 Methodology
    CVSS v3

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    9.9
    EPSS score

    The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“.

    Read in glossary
    0.3 %
    Low — model estimates < 1% exploitation likelihood.
    EPSS percentile

    The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking.

    Read in glossary
    24.7
    Elevated — this CVE ranks above at least 10% of all CVEs scored today.
    KEV status

    The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching.

    Read in glossary
    —
    Published
    CWE

    CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect.

    Read in glossary
    CWE-269, CWE-345, CWE-441

    Detection rules

    No NEOSEC detection rule is available for this vulnerability yet.

    Classification under NIS2 and CRA

    Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

    NIS2

    NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management.

    Read in glossary
    High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
    CRA

    The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates.

    Read in glossary
    From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
    ISO/IEC 27001

    ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security.

    Read in glossary
    Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

    Description

    Summary

    An authenticated user with internal_user privileges can escalate to proxy_admin and achieve remote code execution. The proxy uses one encryption key for two purposes: sealing secrets at rest and minting session tokens. An attacker exploits this by requesting a new API key with a crafted metadata field containing a forged admin credential as the "secret" value. The proxy encrypts and returns this payload. When this value is then presented as a bearer token, the proxy decrypts it, trusts the forged admin identity, and grants full administrative access, including the ability to execute arbitrary commands via the MCP stdio endpoint.

    Affected versions

    Versions later than 1.91.0 are exploitable in the default configuration. Versions 1.87.0 through 1.90.x are exploitable only if EXPERIMENTAL_UI_LOGIN=true was explicitly set.

    Mitigation

    Upgrade to a patched version as soon as possible.

    If you cannot upgrade immediately, set EXPERIMENTAL_UI_LOGIN=false. This disables the vulnerable authentication path but also breaks CLI SSO and Claude Code gateway login.

    Impact

    An internal user can escalate to proxy admin and execute arbitrary commands on the host.

    Discovery Credit: Hoa X. Nguyen (OPSWAT Unit 515)

    Source: BSI WID Portal

    Affected products

    The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

    Affected products
    Affected versionsFixed in
    BerriAIlitellm
    • ≥ 1.87.0, < 1.100.4
    • —
    Open SourceLiteLLM
    • < 1.100.4
    • < 1.101.3
    • < 1.102.2
    • < 1.103.1
    • < 1.104.0rc2
    • 1.100.4
    • 1.101.3
    • 1.102.2
    • 1.103.1
    • 1.104.0rc2
    piplitellm
    • >= 1.101.0, < 1.101.3
    • >= 1.102.0, < 1.102.2
    • >= 1.103.0, < 1.103.1
    • >= 1.104.0rc1, < 1.104.0rc2
    • >= 1.91.0, < 1.100.4
    • 1.101.3
    • 1.102.2
    • 1.103.1
    • 1.104.0rc2
    • 1.100.4
    pypilitellm
    • 1.100.0
    • 1.100.0.dev1
    • 1.100.0.dev2
    • 1.100.0rc1
    • 1.100.1
    • 1.100.2
    • 1.100.3
    • 1.101.0
    • 1.101.1
    • 1.101.2
    • 1.102.0
    • 1.102.1
    • 1.103.0
    • 1.104.0rc1
    • 1.91.0
    • 1.91.1
    • 1.91.2
    • 1.91.3
    • 1.91.4
    • 1.91.5
    • 1.92.0
    • 1.92.0.dev1
    • 1.92.0.dev2
    • 1.92.0rc1
    • 1.92.0rc2
    • 1.92.1
    • 1.92.2
    • 1.93.0
    • 1.93.0.dev1
    • 1.93.0.dev2
    • 1.93.0.dev3
    • 1.93.0rc1
    • 1.93.0rc2
    • 1.93.1
    • 1.93.2
    • 1.94.0
    • 1.94.0.dev3
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • 1.101.3
    • —
    • —
    • 1.102.2
    • —
    • 1.103.1
    • 1.104.0rc2
    • 1.100.4
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —

    Vendors and products

    Weakness classes (CWE)

    • CWE-269Improper Privilege Management

      Class

      The product does not properly assign, modify, track, or check privileges for an actor, creating an unintended sphere of control for that actor.

      Entry at MITRE CWE-269

    • CWE-345Insufficient Verification of Data Authenticity

      Class

      The product does not sufficiently verify the origin or authenticity of data, in a way that causes it to accept invalid data.

      Entry at MITRE CWE-345

    • CWE-441Unintended Proxy or Intermediary ('Confused Deputy')

      Class

      The product receives a request, message, or directive from an upstream component, but the product does not sufficiently preserve the original source of the request before forwarding the request to an external actor that is outside of the product's control sphere. This causes the product to appear to be the source of the request, leading it to act as a proxy or other intermediary between the upstream component and the external actor.

      Entry at MITRE CWE-441

    References & sources

    • github.comBerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45x_refsource_CONFIRM, web
    • github.comBerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0x_refsource_MISC, web
    • github.comBerriAI/litellm/commit/9161d7f9d6073603ba61ee4aa5e2c0ef5b37a81bx_refsource_MISC, web
    • github.comBerriAI/litellm/commit/9fa1a641119dd0d4fe43e93622eae5f482ceb63fx_refsource_MISC, web
    • github.comBerriAI/litellm/commit/a80eacacee118fbed54e3d98f239d17a63fac818x_refsource_MISC, web
    • github.comBerriAI/litellm/commit/f7cd90f09e9716652b38daec9f0640cdf49d582bx_refsource_MISC, web
    • github.comBerriAI/litellm/releases/tag/v1.100.4x_refsource_MISC, web
    • github.comBerriAI/litellm/releases/tag/v1.101.3x_refsource_MISC, web
    • github.comBerriAI/litellm/releases/tag/v1.102.2x_refsource_MISC, web
    • github.comBerriAI/litellm/releases/tag/v1.103.1x_refsource_MISC, web
    • github.comBerriAI/litellm/releases/tag/v1.104.0-rc.2x_refsource_MISC, web
    • NVD (NIST)vuln/detail/CVE-2026-114612advisory
    • github.comBerriAI/litellmpackage

    Changes to this CVE

    Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

    1. ReceivedGitHub

      CVSS V3.1: AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

      Weakness type: CWE-345, CWE-441, CWE-269

      Description added or changed

      Show 17 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Descriptionadded
      —
      LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled, while versions after 1.91.0 are exploitable in the default configuration. This issue was fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.
      CVSSadded
      —
      AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
      Weakness type (CWE)added
      —
      CWE-345
      Weakness type (CWE)added
      —
      CWE-441
      Weakness type (CWE)added
      —
      CWE-269
      Affected versions (publisher)added
      —
      New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/114xxx/CVE-2026-114612.json">CVE-2026-114612</a>
      Referenceadded
      —
      https://github.com/BerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0
      Referenceadded
      —
      https://github.com/BerriAI/litellm/commit/9161d7f9d6073603ba61ee4aa5e2c0ef5b37a81b
      Referenceadded
      —
      https://github.com/BerriAI/litellm/commit/9fa1a641119dd0d4fe43e93622eae5f482ceb63f
      Referenceadded
      —
      https://github.com/BerriAI/litellm/commit/a80eacacee118fbed54e3d98f239d17a63fac818
      Referenceadded
      —
      https://github.com/BerriAI/litellm/commit/f7cd90f09e9716652b38daec9f0640cdf49d582b
      Referenceadded
      —
      https://github.com/BerriAI/litellm/releases/tag/v1.100.4
      Referenceadded
      —
      https://github.com/BerriAI/litellm/releases/tag/v1.101.3
      Referenceadded
      —
      https://github.com/BerriAI/litellm/releases/tag/v1.102.2
      Referenceadded
      —
      https://github.com/BerriAI/litellm/releases/tag/v1.103.1
      Referenceadded
      —
      https://github.com/BerriAI/litellm/releases/tag/v1.104.0-rc.2
      Referenceadded
      —
      https://github.com/BerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45

      Source identifier: security-advisories@github.com

    Linked CVEs

    Linked CVEs
    CriticalCVE-2026-114612LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key9.9—
    Embed badge

    Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

    Badge preview for CVE-2026-114612
    <a href="https://intel.neosec.eu/en/cve/CVE-2026-114612"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-114612.svg?lang=en" alt="CVE-2026-114612 – NEOSEC Intel" height="20"></a>