LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid virtual key can place api_base inside the user_config request body to bypass is_request_body_safe, which blocks top-level api_base and base_url but previously did not inspect or reject user_config. Because user_config constructs the outbound router, the nested destination redirects a server-side request to an internal or external host selected by the caller and can expose endpoints the caller cannot otherwise access. This issue is fixed in version 1.83.9.
CVE-2026-59823
MEDIUMPre-NVD 5.35.3—Trending — 3 sources updated this week
EchelonGraph scoreMEDIUM confidence
This medium-severity CVE scores 5.3 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.4%, top 62% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
Triggered by: NVD CVSS baseline
Sources: epss, secondary
5.3EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
- Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 5.3Exploit: None knownExposed: 0
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 5.3
- EG Score
- 5.3(medium)
- EG Risk
- 24(Track)EG Risk 24/100SSVC: Track
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity53% × 45%Exploitation0% × 40%Automatability0% × 15%Action: Routine — remediate on your standard cadence. - EPSS PROB
- 0%
- EPSS %ILE
- 38%
- KEV
- Not listed
Published
September 16, 2026
Last Modified
September 17, 2026
Advisory Details (3)
Auto-updated Sep 16, 2026Patch available. Sources: github, github_pr, github_commit.
github_commit
commit 47214be317f4 (BerriAI/litellm)
Fix landed in BerriAI/litellm commit 47214be317f4 — awaiting tagged release
https://github.com/BerriAI/litellm/commit/47214be317f45a2d2ac08258362e0481411eb427github_pr
fix(proxy): harden request parameter handling
Fix merged in BerriAI/litellm PR #25827 on 2026-04-16 — awaiting tagged release
https://github.com/BerriAI/litellm/pull/25827github Patch Available
Server-side request forgery via the `user_config` request parameter in LiteLLM Proxy · Advisory · BerriAI/litellm · GitHub
https://github.com/BerriAI/litellm/security/advisories/GHSA-hx8v-g79f-8w5fVendor Advisories for CVE-2026-59823(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fixed in | Dependents |
|---|---|---|---|
| litellm | 0.1.0 ... 1.9.dev0 (736 versions) | 1.83.9 | — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 8× in last 7d / 8× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-09-18 20:37 UTCEG score recompute
- 2026-09-18 19:28 UTCEPSS rescore
- 2026-09-17 19:31 UTCEPSS rescore
- 2026-09-17 18:00 UTCEG score recompute
- 2026-09-17 15:26 UTCEG score recompute
- 2026-09-16 19:24 UTCEG score recompute
- 2026-09-16 18:51 UTCEG score recompute
- 2026-09-16 18:49 UTCMITRE cvelistV5first tracked
Related CVEs(same CWE)
Same CWE
10 shownCWE-918
- CVE-2016-10927EG 10.0CRITICAL
- CVE-2016-10926EG 10.0CRITICAL
- CVE-2018-10511EG 10.0CRITICAL
- CVE-2018-1000124EG 10.0CRITICAL
- CVE-2017-11291EG 10.0EPSS p92CRITICAL
- CVE-2017-12905EG 10.0CRITICAL
- CVE-2017-8794EG 10.0CRITICAL
- CVE-2017-13667EG 9.9CRITICAL
- CVE-2017-17674EG 9.8CRITICAL
- CVE-2013-4864EG 9.8EPSS p93CRITICAL
Frequently asked(5)
What is CVE-2026-59823?
CVE-2026-59823 is a medium vulnerability published on September 16, 2026. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid virtual key can place apibase inside the userconfig request body to bypass isrequestbodysafe, which blocks top-level apibase and baseurl but…
When was CVE-2026-59823 disclosed?
CVE-2026-59823 was first published in the National Vulnerability Database on September 16, 2026, with the most recent update on September 17, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-59823 actively exploited?
CVE-2026-59823 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 62.4% of all scored CVEs.
What is the CVSS score of CVE-2026-59823?
CVE-2026-59823 has a CVSS v3 base score of 5.3 (NVD).
How do I remediate CVE-2026-59823?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-59823, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-59823
Is Your Infrastructure Affected by CVE-2026-59823?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.