CVE-2026-84377

MEDIUMPre-NVD 6.56.5—
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 6.5 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.3%, top 76% 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
6.5EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 6.5Exploit: None knownExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator's stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.

CVSS v3
6.5
EG Score
6.5(medium)
EG Risk
29(Track)
EG Risk 29/100SSVC: 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 computed
Severity65% × 45%
Exploitation0% × 40%
Automatability0% × 15%
Action: Routine — remediate on your standard cadence.
EPSS PROB
0%
EPSS %ILE
24%
KEV
Not listed

Published

September 2, 2026

Last Modified

September 9, 2026

Advisory Details (9)

Auto-updated Sep 2, 2026
Patch available. Sources: github, github_pr, github_commit, github_release.
github_release Patch Available

v1.96.2

Patch available: BerriAI/litellm v1.96.2

https://github.com/BerriAI/litellm/releases/tag/v1.96.2
github_release Patch Available

v1.88.6

Patch available: BerriAI/litellm v1.88.6

https://github.com/BerriAI/litellm/releases/tag/v1.88.6
github_commit

commit c898d341c022 (BerriAI/litellm)

Fix landed in BerriAI/litellm commit c898d341c022 — awaiting tagged release

https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593
github_commit

commit 820f247a6abb (BerriAI/litellm)

Fix landed in BerriAI/litellm commit 820f247a6abb — awaiting tagged release

https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37
github_commit

commit 473f72e63a97 (BerriAI/litellm)

Fix landed in BerriAI/litellm commit 473f72e63a97 — awaiting tagged release

https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b
github_pr

chore(release): backport proxy request-handling maintenance and refresh runtime deps for 1.96.1

Fix merged in BerriAI/litellm PR #36494 on 2026-08-11 — awaiting tagged release

https://github.com/BerriAI/litellm/pull/36494
github_pr

chore(release): backport proxy request-handling fixes and refresh runtime deps for 1.88.6

Fix merged in BerriAI/litellm PR #36314 on 2026-08-08 — awaiting tagged release

https://github.com/BerriAI/litellm/pull/36314
github_pr

fix(proxy)!: apply request-parameter checks consistently across body, path and form inputs

Fix merged in BerriAI/litellm PR #36011 on 2026-08-05 — awaiting tagged release

https://github.com/BerriAI/litellm/pull/36011
github Patch Available

Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 13× in last 7d / 31× 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.

  1. 2026-09-20 20:50 UTCEG score recompute
  2. 2026-09-20 20:16 UTCEPSS rescore
  3. 2026-09-19 21:07 UTCEG score recompute
  4. 2026-09-18 21:24 UTCEG score recompute
  5. 2026-09-18 19:28 UTCEPSS rescore
  6. 2026-09-17 20:37 UTCEG score recompute
  7. 2026-09-17 19:32 UTCEPSS rescore
  8. 2026-09-16 19:27 UTCEG score recompute
  9. 2026-09-16 14:09 UTCEPSS rescore
  10. 2026-09-16 05:15 UTCEPSS rescore
  11. 2026-09-15 19:44 UTCEG score recompute
  12. 2026-09-15 03:12 UTCEPSS rescore
  13. 2026-09-15 03:12 UTCEPSS rescore
  14. 2026-09-13 20:14 UTCEG score recompute
  15. 2026-09-12 20:31 UTCEG score recompute
  16. 2026-09-11 20:48 UTCEG score recompute
  17. 2026-09-11 14:53 UTCEPSS rescore
  18. 2026-09-11 14:53 UTCEPSS rescore
  19. 2026-09-10 20:54 UTCEG score recompute
  20. 2026-09-08 23:11 UTCEG score recompute
  21. 2026-09-08 22:01 UTCEPSS rescore
  22. 2026-09-06 14:41 UTCEG score recompute
  23. 2026-09-06 13:48 UTCEPSS rescore
  24. 2026-09-05 15:31 UTCEPSS rescore
  25. 2026-09-04 15:14 UTCEG score recompute
Show 6 more
  1. 2026-09-04 05:07 UTCEPSS rescore
  2. 2026-09-03 15:31 UTCEG score recompute
  3. 2026-09-03 14:35 UTCEG score recompute
  4. 2026-09-02 18:36 UTCEG score recompute
  5. 2026-09-02 17:33 UTCEG score recompute
  6. 2026-09-02 17:31 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-84377?
CVE-2026-84377 is a medium vulnerability published on September 2, 2026. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials…
When was CVE-2026-84377 disclosed?
CVE-2026-84377 was first published in the National Vulnerability Database on September 2, 2026, with the most recent update on September 9, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-84377 actively exploited?
CVE-2026-84377 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 75.6% of all scored CVEs.
What is the CVSS score of CVE-2026-84377?
CVE-2026-84377 has a CVSS v3 base score of 6.5 (NVD).
How do I remediate CVE-2026-84377?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-84377, 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

Explore the affected products and dependency analysis for CVE-2026-84377

Explore →

Is Your Infrastructure Affected by CVE-2026-84377?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs