cve.bz

CVE-2026-108575 berriai litellm: Incorrect Privilege Assignment

2.1 lowEPSS 0.2%

Low (2.1) in berriai litellm. EPSS 0.2% estimated probability of exploitation activity in the next 30 days.

On this page
A vulnerability has been found in BerriAI LiteLLM up to 1.94.0. This affects the function get_secret of the file secret_managers/main.py of the component Secret Resolution. The manipulation of the argument api_key leads to improper authorization. The attack can be initiated remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

Severity

CVSS 4.0

2.1 low
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

CVSS 3.1

6.3 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
EPSS
0.2% (unchanged from 0.2% a week ago; 0.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 10th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-10-15. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-266 Incorrect Privilege Assignment
CWE-285 Improper Authorization
OWASP Top 10
A01:2025 Broken Access Control, A06:2025 Insecure Design
Published
Modified
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Ask an AI about this CVE

Show the promptExplain CVE-2026-108575 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-108575?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-108575?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-2026-108575 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.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
BerriAI LiteLLM1.0
BerriAI LiteLLM1.1
BerriAI LiteLLM1.2
BerriAI LiteLLM1.3
BerriAI LiteLLM1.4
BerriAI LiteLLM1.5
BerriAI LiteLLM1.6
BerriAI LiteLLM1.7
BerriAI LiteLLM1.8
BerriAI LiteLLM1.9
BerriAI LiteLLM1.10
BerriAI LiteLLM1.11
BerriAI LiteLLM1.12
BerriAI LiteLLM1.13
BerriAI LiteLLM1.14
BerriAI LiteLLM1.15
BerriAI LiteLLM1.16
BerriAI LiteLLM1.17
BerriAI LiteLLM1.18
BerriAI LiteLLM1.19
BerriAI LiteLLM1.20
BerriAI LiteLLM1.21
BerriAI LiteLLM1.22
BerriAI LiteLLM1.23
BerriAI LiteLLM1.24
BerriAI LiteLLM1.25
BerriAI LiteLLM1.26
BerriAI LiteLLM1.27
BerriAI LiteLLM1.28
BerriAI LiteLLM1.29
BerriAI LiteLLM1.30
BerriAI LiteLLM1.31
BerriAI LiteLLM1.32
BerriAI LiteLLM1.33
BerriAI LiteLLM1.34
BerriAI LiteLLM1.35
BerriAI LiteLLM1.36
BerriAI LiteLLM1.37
BerriAI LiteLLM1.38
BerriAI LiteLLM1.39
BerriAI LiteLLM1.40
BerriAI LiteLLM1.41
BerriAI LiteLLM1.42
BerriAI LiteLLM1.43
BerriAI LiteLLM1.44
BerriAI LiteLLM1.45
BerriAI LiteLLM1.46
BerriAI LiteLLM1.47
BerriAI LiteLLM1.48
BerriAI LiteLLM1.49
BerriAI LiteLLM1.50
BerriAI LiteLLM1.51
BerriAI LiteLLM1.52
BerriAI LiteLLM1.53
BerriAI LiteLLM1.54
BerriAI LiteLLM1.55
BerriAI LiteLLM1.56
BerriAI LiteLLM1.57
BerriAI LiteLLM1.58
BerriAI LiteLLM1.59
BerriAI LiteLLM1.60
BerriAI LiteLLM1.61
BerriAI LiteLLM1.62
BerriAI LiteLLM1.63
BerriAI LiteLLM1.64
BerriAI LiteLLM1.65
BerriAI LiteLLM1.66
BerriAI LiteLLM1.67
BerriAI LiteLLM1.68
BerriAI LiteLLM1.69
BerriAI LiteLLM1.70
BerriAI LiteLLM1.71
BerriAI LiteLLM1.72
BerriAI LiteLLM1.73
BerriAI LiteLLM1.74
BerriAI LiteLLM1.75
BerriAI LiteLLM1.76
BerriAI LiteLLM1.77
BerriAI LiteLLM1.78
BerriAI LiteLLM1.79
BerriAI LiteLLM1.80
BerriAI LiteLLM1.81
BerriAI LiteLLM1.82
BerriAI LiteLLM1.83
BerriAI LiteLLM1.84
BerriAI LiteLLM1.85
BerriAI LiteLLM1.86
BerriAI LiteLLM1.87
BerriAI LiteLLM1.88
BerriAI LiteLLM1.89
BerriAI LiteLLM1.90
BerriAI LiteLLM1.91
BerriAI LiteLLM1.92
BerriAI LiteLLM1.93
BerriAI LiteLLM1.94.0

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

A moderate-impact flaw was found in the LiteLLM (litellm) library, which Red Hat ships as a dependency in products including Red Hat OpenShift AI, Ansible Automation Platform (Lightspeed chatbot images), Lightspeed Core, and Red Hat Insights/Ansible Lightspeed services. The vulnerability lies in the get_secret function of LiteLLM's secret resolution mechanism (secret_managers/main.py): a remote attacker with valid API credentials can manipulate the api_key parameter to bypass authorization controls, potentially accessing secrets or other protected resources beyond what their credentials authorize. Red Hat rates this flaw as moderate severity, CVSS 6.3 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L), reflecting that exploitation requires an authenticated account and has limited impact on confidentiality, integrity, and availability; this differs from the CVEORG CVSS 4.0 assessment of 2.1 (low), which results from the CVSS 4.0 model's weighting of partial impact metrics. Because the impact is moderate with a CVSS score below 7.0, fixes for the affected in-support streams are deferred per Red Hat's moderate-severity handling, leaving the residual risk that an authenticated user could bypass secret-resolution authorization and retrieve protected secrets. The services-lightspeed-agent-google-cloud stream, which bundles litellm but is not within Red Hat's full support scope, is out of support scope for this flaw.

Red Hat's 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.

ProductPackageStateAdvisory
Lightspeed Corelightspeed-core/lightspeed-stack-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-26/lightspeed-chatbot-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/lightspeed-chatbot-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-llama-stack-core-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-mlflow-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-th-torch-cpu-py312-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-th-torch-cuda-py312-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Fix 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-2026-108575.

Attack patterns (CAPEC)

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).

References

Check your stackJSON