CVSS 4.0
8.7 highCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NHigh (8.7) in litellm litellm. EPSS 0.7% estimated probability of exploitation activity in the next 30 days. Fixed in litellm 1.83.10.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:Hlitellm (PyPI): fixed in 1.83.10Explain CVE-2026-47102 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-47102?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-47102?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-2026-47102 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 | before 1.83.10 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-wpfp-gwwc-vwq6 | PyPI | litellm | <1.83.10 | 1.83.10 |
| PYSEC-2026-2600 | PyPI | litellm | <1.83.10 | 1.83.10 |
Red Hat rates this Important.
This vulnerability is rated Important because an authenticated LiteLLM proxy user may be able to modify their own user_role via the /user/update endpoint and escalate to proxy_admin, gaining full administrative access to the LiteLLM instance.
Exploitation requires network access to a LiteLLM proxy deployment and valid credentials for a user who can reach the user management endpoints. Users with the org_admin role can exploit this directly. Products that bundle litellm without exposing the proxy user-management API have reduced exposure. Affected packages should be updated to litellm 1.83.10 or later when fixes are released.
Update the litellm package to version 1.83.10 or later.
Until updated builds are available, restrict access to LiteLLM proxy /user/update and /user/bulk_update endpoints so only trusted administrators can modify user accounts. Audit user_role assignments for unexpected proxy_admin promotions.
| Product | Package | State | Advisory |
|---|---|---|---|
| Exploit Intelligence | exploit-intelligence-tech-preview/vulnerability-analysis-rhel9 | Affected | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-26/lightspeed-chatbot-rhel9 | Not affected | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-27/lightspeed-chatbot-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-llama-stack-core-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-mlflow-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9 | Not affected |
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-2026-47102.
Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.