LiveActive security incident?Get immediate response
CVE Record

CVE-2026-35029: LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment variables, register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution, read arbitrary server files by setting UI_LOGO_PATH and fetching via /get_image, and take over other privileged accounts by overwriting UI_USERNAME and UI_PASSWORD environment variables. Fixed in v1.83.0.

HighCVSS 8.8Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

LiteLLM versions before 1.83.0 let any authenticated platform user change proxy configuration without admin authorization. That can escalate a low-privileged account into control of the AI gateway, including remote code execution, server file reads, and takeover of privileged UI accounts.

Executive priority

Treat this as urgent for any LiteLLM gateway with multiple users or network exposure. A compromised ordinary account could become control of the AI proxy and underlying server context.

Technical view

The vulnerable /config/update endpoint lacks proper admin role enforcement. With valid authentication, an attacker can alter proxy configuration and environment variables, register custom pass-through endpoint handlers, abuse UI_LOGO_PATH for file reads via /get_image, and overwrite UI_USERNAME/UI_PASSWORD. The issue is fixed in LiteLLM 1.83.0.

Likely exposure

Exposure is limited to deployments running BerriAI LiteLLM before 1.83.0 where untrusted or lower-privileged users can authenticate. Internet exposure of the LiteLLM proxy or broad internal user access increases risk.

Exploitation context

The provided sources do not show CISA KEV listing or active exploitation evidence. Exploitation requires a valid authenticated account, but no user interaction and low complexity are indicated by CVSS 3.1 score 8.8.

Researcher notes

Focus validation on authorization bypass at /config/update, configuration drift, environment-variable changes, unexpected handler registrations, and file-access indicators through /get_image. Avoid assuming unauthenticated exposure; the source description requires an already authenticated user.

Mitigation direction

  • Upgrade LiteLLM to version 1.83.0 or later.
  • Restrict LiteLLM administrative and management surfaces to trusted administrators.
  • Review vendor and Red Hat advisories for product-specific packages and errata.
  • Rotate administrative credentials and connected secrets if suspicious configuration changes are found.

Validation and detection

  • Inventory all LiteLLM deployments and confirm installed versions.
  • Review logs for non-admin requests to /config/update.
  • Check for unexpected custom pass-through handlers or environment-variable overrides.
  • Verify UI_USERNAME, UI_PASSWORD, and UI_LOGO_PATH were not unexpectedly changed.
  • Confirm Red Hat affected products are remediated through applicable errata.
Prepared
Confidence
high
Sources
9

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · low confidence lookup

CWE-425: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cwe · medium confidence lookup

CWE-863: Authorization and privilege behavior lookup

Authorization weaknesses can support privilege escalation and valid-account review, depending on exploit path. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Execution behavior lookup

The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
description · low confidence lookup

Privilege behavior lookup

The CVE wording references privilege impact, so privilege escalation and authorization behavior review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-35029 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
8.8 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
5Timeline events
3ADP providers
8Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: total

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
8.8CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H2.85.9redhat-SADP
8.7CVSS 4.0HighCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:L/SI:L/SA:N——GitHub_M

Vulnerability scoring details

Base CVSS 4.0 score

8.7High
CVSS 4.0 vector shape for CVE-2026-35029Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:L/SI:L/SA:N

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
CVECVE Program Container
redhat-SADPlitellm: LiteLLM: Remote code execution and privilege escalation via unrestricted proxy configuration endpoint
other:Red Hat severity ratingcvssV3_1
  • 2026-04-06T17:01:57.502Z: Reported to Red Hat.
  • 2026-04-06T16:35:28.974Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
BerriAIlitellm< 1.83.0Listed
Weakness

CWE details

CWE-425CWE-863

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-425 · source CWE mapping

Direct Request ('Forced Browsing')

Direct Request ('Forced Browsing') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs
CWE-863 · source CWE mapping

Incorrect Authorization

Incorrect Authorization represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs