CVE-2026-108574
Description
A flaw was found in LiteLLM. A remote attacker can bypass authorization controls by manipulating the session identifier (session_id) parameter in the spend tracking interface. This flaw allows an attacker to view spend tracking logs and usage metrics associated with other user sessions without proper authorization.
Statement
A MODERATE severity authorization bypass flaw was found in the BerriAI LiteLLM spend tracking component. The ui_view_session_spend_logs function in litellm/proxy/spend_tracking/spend_management_endpoints.py does not properly verify that the requesting user is authorized to view a given session, so an authenticated remote attacker can manipulate the session_id parameter to view spend tracking logs and usage metrics belonging to other users' sessions. The impact is limited to the confidentiality of spend and usage data; there is no impact on integrity or availability (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N). Red Hat products that bundle litellm, including Red Hat OpenShift AI, Ansible Automation Platform lightspeed chatbot offerings, Lightspeed Core, and related Lightspeed/Insights and Ansible Services offerings, are affected. Because the impact is MODERATE with a CVSS score below 7.0, fixes for these products are deferred and no trackers are being filed; the residual risk is that an authenticated user may read spend tracking logs and usage metrics of other users' sessions. The services-lightspeed-agent-google-cloud stream is out of support scope. Red Hat rates this issue MODERATE (CVSS 4.3); the upstream CVSS 4.0 score is 2.1 (LOW), while the upstream CVSS 3.1 score of 4.3 matches the Red Hat assessment.
Mitigation
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. The upstream LiteLLM project has addressed this flaw in version 1.96.0; upgrading to a release that includes this fix resolves the issue for direct upstream deployments.
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 | 4.3 | N/A | 4.3 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | Low | N/A | Low |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | Low | N/A | Low |
| Integrity Impact | None | N/A | None |
| Availability Impact | None | N/A | None |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
cve.org: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N/E:P/RL:O/RC:C
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
