CVE-2026-59821
Description
A flaw was found in LiteLLM, a proxy server for Large Language Model (LLM) APIs. A privileged user with access to create or update custom code guardrails could exploit this vulnerability. The flaw allowed the user to submit custom Python code that would execute within the LiteLLM proxy environment, potentially exposing sensitive information or secrets accessible to the process.
Statement
Red Hat rates this flaw with higher severity than the upstream GitHub Security Advisory (GHSA-72m8-9m7m-h278, CVSS v4.0 2.1, Low). Red Hat scored this CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H (7.2, Important) because a successful exploit grants arbitrary Python code execution within the LiteLLM proxy process, resulting in full compromise of the confidentiality, integrity, and availability of that component, including exposure of any secrets accessible to the process. Exploitation requires an authenticated caller with privileges to create or update LiteLLM Custom Code Guardrails, which is a proxy-administrator-level capability in default configurations.
Mitigation
Upgrade litellm to 1.82.0 or later, which enforces the same code-safety checks on the guardrail create/update endpoints as the test endpoint. If upgrading is not immediately possible, restrict access to POST /guardrails and PUT /guardrails/{guardrail_id} to trusted administrators only, ensure LITELLM_MASTER_KEY is configured so unauthenticated callers are not treated as proxy administrators, and avoid enabling Custom Code Guardrails for untrusted users.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
The following CVSS metrics and score provided are preliminary and subject to review.
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 7.2 | 7.2 | N/A |
| Attack Vector | Network | Network | N/A |
| Attack Complexity | Low | Low | N/A |
| Privileges Required | High | High | N/A |
| User Interaction | None | None | N/A |
| Scope | Unchanged | Unchanged | N/A |
| Confidentiality | High | High | N/A |
| Integrity Impact | High | High | N/A |
| Availability Impact | High | High | N/A |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H
NVD: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H
Understanding the Weakness (CWE)
Access Control
Technical Impact: Bypass Protection Mechanism
In some cases, injectable code controls authentication; this may lead to a remote vulnerability.
Access Control
Technical Impact: Gain Privileges or Assume Identity
Injected code can access resources that the attacker is directly prevented from accessing.
Integrity,Confidentiality,Availability
Technical Impact: Execute Unauthorized Code or Commands
When a product allows a user's input to contain code syntax, it might be possible for an attacker to craft the code in such a way that it will alter the intended control flow of the product. As a result, code injection can often result in the execution of arbitrary code. Code injection attacks can also lead to loss of data integrity in nearly all cases, since the control-plane data injected is always incidental to data recall or writing.
Non-Repudiation
Technical Impact: Hide Activities
Often the actions performed by injected control code are unlogged.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
