CVE-2026-54033

MEDIUMNVD 6.56.5—
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 6.5 under NVD CVSS v3. EPSS exploit probability: 0.2%, top 89% 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, nvd
6.5
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS: 0%CVSS: 6.5Exploit: NoneExposed: 0

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

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, LibreChat allows users to configure custom OpenAI-compatible API endpoints by setting a baseURL. This URL is used to construct HTTP requests without any SSRF validation — no private IP check, no scheme restriction, no DNS pinning. An authenticated user can set baseURL to internal network addresses. This vulnerability is fixed in 0.8.4-rc1.

CVSS v3
6.5
EG Score
6.5(medium)
EPSS
10.8%
KEV
Not listed

Published

June 25, 2026

Last Modified

June 29, 2026

Advisory Details (1)

Auto-updated Jun 25, 2026
🔬 Proof of concept available. Patch available. Sources: github.
github Patch Available🟡 PoC Available

SSRF via User-Provided Custom Endpoint baseURL — no private IP validation on user-configured API base URLs · Advisory · danny-avila/LibreChat · GitHub

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gc9r-88c3-7qhq

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 19× in last 7d / 53× 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. 2026-07-13 22:31 UTCEPSS rescore
  2. 2026-07-13 19:26 UTCEG score recompute
  3. 2026-07-13 06:13 UTCEPSS rescore
  4. 2026-07-13 06:13 UTCEPSS rescore
  5. 2026-07-12 20:02 UTCEG score recompute
  6. 2026-07-12 05:46 UTCEPSS rescore
  7. 2026-07-11 20:36 UTCEG score recompute
  8. 2026-07-11 08:27 UTCEPSS rescore
  9. 2026-07-11 08:27 UTCEPSS rescore
  10. 2026-07-10 21:12 UTCEG score recompute
  11. 2026-07-09 21:47 UTCEG score recompute
  12. 2026-07-09 19:10 UTCEPSS rescore
  13. 2026-07-09 19:10 UTCEPSS rescore
  14. 2026-07-08 22:22 UTCEG score recompute
  15. 2026-07-08 15:16 UTCEPSS rescore
  16. 2026-07-08 15:16 UTCEPSS rescore
  17. 2026-07-07 22:58 UTCEG score recompute
  18. 2026-07-07 13:46 UTCEPSS rescore
  19. 2026-07-07 13:46 UTCEPSS rescore
  20. 2026-07-06 23:35 UTCEG score recompute
  21. 2026-07-06 16:27 UTCEPSS rescore
  22. 2026-07-06 16:27 UTCEPSS rescore
  23. 2026-07-06 02:23 UTCEPSS rescore
  24. 2026-07-06 02:23 UTCEPSS rescore
  25. 2026-07-06 00:11 UTCEG score recompute
Show 28 more
  1. 2026-07-05 02:31 UTCEPSS rescore
  2. 2026-07-05 02:30 UTCEPSS rescore
  3. 2026-07-05 00:48 UTCEG score recompute
  4. 2026-07-04 06:31 UTCEPSS rescore
  5. 2026-07-04 06:31 UTCEPSS rescore
  6. 2026-07-04 01:23 UTCEG score recompute
  7. 2026-07-03 01:59 UTCEG score recompute
  8. 2026-07-02 02:35 UTCEG score recompute
  9. 2026-07-01 15:07 UTCEPSS rescore
  10. 2026-07-01 03:11 UTCEG score recompute
  11. 2026-06-30 23:22 UTCEPSS rescore
  12. 2026-06-30 03:47 UTCEG score recompute▼ 1.20
  13. 2026-06-29 16:05 UTCNVD updateCVSS v3 → 6.5 · severity → MEDIUM
  14. 2026-06-29 15:06 UTCEG score recompute
  15. 2026-06-29 14:06 UTCEPSS rescore
  16. 2026-06-29 14:06 UTCEPSS rescore
  17. 2026-06-29 02:25 UTCEG score recompute
  18. 2026-06-28 14:07 UTCEPSS rescore
  19. 2026-06-28 13:43 UTCEG score recompute
  20. 2026-06-28 04:56 UTCEPSS rescore
  21. 2026-06-28 04:56 UTCEPSS rescore
  22. 2026-06-28 01:02 UTCEG score recompute
  23. 2026-06-27 12:20 UTCEG score recompute
  24. 2026-06-27 03:08 UTCEPSS rescore
  25. 2026-06-26 23:38 UTCEG score recompute
  26. 2026-06-26 10:57 UTCEG score recompute
  27. 2026-06-25 17:51 UTCEG score recompute
  28. 2026-06-25 17:48 UTCNVD updatefirst tracked

Frequently asked(5)

What is CVE-2026-54033?
CVE-2026-54033 is a medium vulnerability published on June 25, 2026. LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, LibreChat allows users to configure custom OpenAI-compatible API endpoints by setting a baseURL. This URL is used to construct HTTP requests without any SSRF validation — no private IP check, no scheme…
When was CVE-2026-54033 disclosed?
CVE-2026-54033 was first published in the National Vulnerability Database on June 25, 2026, with the most recent update on June 29, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-54033 actively exploited?
CVE-2026-54033 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 10.8% percentile likelihood of exploitation in the next 30 days — higher percentiles indicate greater predicted risk.
What is the CVSS score of CVE-2026-54033?
CVE-2026-54033 has a CVSS v3 base score of 6.5 (NVD).
How do I remediate CVE-2026-54033?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-54033, 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-2026-54033

Explore →

Is Your Infrastructure Affected by CVE-2026-54033?

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

Start Free Scan →Browse All CVEs