Raw 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-35029 is a high-severity Incorrect Authorization (CWE-863) vulnerability in Litellm Litellm. Its CVSS base score is 8.7 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked in the top 2% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified map to AC-24 (Access Control Decisions) and AC-25 (Reference Monitor) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
LiteLLM is an AI gateway proxy server that routes calls to LLM APIs using OpenAI-compatible or native formats. Prior to version 1.83.0 the /config/update endpoint failed to enforce admin-role authorization checks, a flaw tracked as CWE-863. Any authenticated user could therefore alter proxy settings and environment variables through this endpoint.
An attacker already logged into the platform can register custom pass-through handlers that point to attacker-controlled Python code, resulting in remote code execution. The same access also permits reading arbitrary files by setting UI_LOGO_PATH and retrieving them via /get_image, as well as account takeover by overwriting UI_USERNAME and UI_PASSWORD variables.
The GitHub security advisory GHSA-53mr-6c8q-9789 states that the issue is resolved in LiteLLM v1.83.0.
The associated EPSS score rose from lower values after the April 2026 disclosure to a peak of 0.2593 on 22 May 2026 before receding to the current 0.1938, indicating a period of increased exploitation interest in this LLM-gateway component.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-19370
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, llm, openai
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 5 hardening rules · 3 OS baselines
—
Mitigating Controls (NIST 800-53 r5) AI
AC-3 directly requires correct enforcement of authorization decisions on every access request, structurally preventing incorrect checks.
AC-24 ensures access-control decisions are made and applied consistently, reducing the chance of an incorrect authorization result.
A reference monitor that is always invoked and tamper-proof forces every authorization decision through a verified, correct path.
Least-privilege assignments shrink the set of authorizations that must be checked correctly, limiting exposure to flawed checks.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing can detect forced-browsing flaws, but the control itself does not prevent them in production.
Information access restriction implements the technical enforcement that directly blocks unauthorized direct requests.
Requiring consistency between access rights and classification plus formal approval steps ensures that the authorization logic correctly distinguishes between entities that should and should not be granted access.
Enforcing policy-driven approval and role-change reviews stops incorrect or stale authorization decisions from remaining in effect after job changes or terminations.
Privileged access rights control enforces least-privilege checks on restricted endpoints.
Secure SDLC can include authorization design, yet the control itself does not guarantee runtime enforcement.
Hardening callouts derived
Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).
Oracle Linux 8 (2 rules)
- V-248581 OL 8 must require users to provide a password for privilege escalation. prevents CWE-863
- V-252656 The OL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-863
RHEL 7 (1 rule)
- V-204430 The Red Hat Enterprise Linux operating system must be configured so that users must re-authenticate for privilege escalation. prevents CWE-863
RHEL 8 (1 rule)
- V-251712 The RHEL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-863