CVSS 4.0
2.1 lowCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:PLow (2.1) in berriai litellm. EPSS 0.2% estimated probability of exploitation activity in the next 30 days.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:PCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:NExplain CVE-2026-108574 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-108574?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-108574?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-108574 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
From the CNA's record in the CVE List.
| Product | Affected |
|---|---|
| BerriAI LiteLLM | 1.0 |
| BerriAI LiteLLM | 1.1 |
| BerriAI LiteLLM | 1.2 |
| BerriAI LiteLLM | 1.3 |
| BerriAI LiteLLM | 1.4 |
| BerriAI LiteLLM | 1.5 |
| BerriAI LiteLLM | 1.6 |
| BerriAI LiteLLM | 1.7 |
| BerriAI LiteLLM | 1.8 |
| BerriAI LiteLLM | 1.9 |
| BerriAI LiteLLM | 1.10 |
| BerriAI LiteLLM | 1.11 |
| BerriAI LiteLLM | 1.12 |
| BerriAI LiteLLM | 1.13 |
| BerriAI LiteLLM | 1.14 |
| BerriAI LiteLLM | 1.15 |
| BerriAI LiteLLM | 1.16 |
| BerriAI LiteLLM | 1.17 |
| BerriAI LiteLLM | 1.18 |
| BerriAI LiteLLM | 1.19 |
| BerriAI LiteLLM | 1.20 |
| BerriAI LiteLLM | 1.21 |
| BerriAI LiteLLM | 1.22 |
| BerriAI LiteLLM | 1.23 |
| BerriAI LiteLLM | 1.24 |
| BerriAI LiteLLM | 1.25 |
| BerriAI LiteLLM | 1.26 |
| BerriAI LiteLLM | 1.27 |
| BerriAI LiteLLM | 1.28 |
| BerriAI LiteLLM | 1.29 |
| BerriAI LiteLLM | 1.30 |
| BerriAI LiteLLM | 1.31 |
| BerriAI LiteLLM | 1.32 |
| BerriAI LiteLLM | 1.33 |
| BerriAI LiteLLM | 1.34 |
| BerriAI LiteLLM | 1.35 |
| BerriAI LiteLLM | 1.36 |
| BerriAI LiteLLM | 1.37 |
| BerriAI LiteLLM | 1.38 |
| BerriAI LiteLLM | 1.39 |
| BerriAI LiteLLM | 1.40 |
| BerriAI LiteLLM | 1.41 |
| BerriAI LiteLLM | 1.42 |
| BerriAI LiteLLM | 1.43 |
| BerriAI LiteLLM | 1.44 |
| BerriAI LiteLLM | 1.45 |
| BerriAI LiteLLM | 1.46 |
| BerriAI LiteLLM | 1.47 |
| BerriAI LiteLLM | 1.48 |
| BerriAI LiteLLM | 1.49 |
| BerriAI LiteLLM | 1.50 |
| BerriAI LiteLLM | 1.51 |
| BerriAI LiteLLM | 1.52 |
| BerriAI LiteLLM | 1.53 |
| BerriAI LiteLLM | 1.54 |
| BerriAI LiteLLM | 1.55 |
| BerriAI LiteLLM | 1.56 |
| BerriAI LiteLLM | 1.57 |
| BerriAI LiteLLM | 1.58 |
| BerriAI LiteLLM | 1.59 |
| BerriAI LiteLLM | 1.60 |
| BerriAI LiteLLM | 1.61 |
| BerriAI LiteLLM | 1.62 |
| BerriAI LiteLLM | 1.63 |
| BerriAI LiteLLM | 1.64 |
| BerriAI LiteLLM | 1.65 |
| BerriAI LiteLLM | 1.66 |
| BerriAI LiteLLM | 1.67 |
| BerriAI LiteLLM | 1.68 |
| BerriAI LiteLLM | 1.69 |
| BerriAI LiteLLM | 1.70 |
| BerriAI LiteLLM | 1.71 |
| BerriAI LiteLLM | 1.72 |
| BerriAI LiteLLM | 1.73 |
| BerriAI LiteLLM | 1.74 |
| BerriAI LiteLLM | 1.75 |
| BerriAI LiteLLM | 1.76 |
| BerriAI LiteLLM | 1.77 |
| BerriAI LiteLLM | 1.78 |
| BerriAI LiteLLM | 1.79 |
| BerriAI LiteLLM | 1.80 |
| BerriAI LiteLLM | 1.81 |
| BerriAI LiteLLM | 1.82 |
| BerriAI LiteLLM | 1.83 |
| BerriAI LiteLLM | 1.84 |
| BerriAI LiteLLM | 1.85 |
| BerriAI LiteLLM | 1.86 |
| BerriAI LiteLLM | 1.87 |
| BerriAI LiteLLM | 1.88 |
| BerriAI LiteLLM | 1.89 |
| BerriAI LiteLLM | 1.90 |
| BerriAI LiteLLM | 1.91 |
| BerriAI LiteLLM | 1.92 |
| BerriAI LiteLLM | 1.93 |
| BerriAI LiteLLM | 1.94 |
| BerriAI LiteLLM | 1.95.0 |
Red Hat rates this Moderate.
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 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.
| Product | Package | State | Advisory |
|---|---|---|---|
| Lightspeed Core | lightspeed-core/lightspeed-stack-rhel9 | Fix deferred | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-26/lightspeed-chatbot-rhel9 | Fix deferred | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-27/lightspeed-chatbot-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-llama-stack-core-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-mlflow-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-th-torch-cpu-py312-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-th-torch-cuda-py312-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9 | Fix deferred |
Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-108574.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-285 (16).