CVE-2026-31945: LibreChat is a ChatGPT clone with additional features

Routine

HIGH 7.7DOWNGRADE

CVE-2026-31945 is a high-severity flaw (CVSS 7.7) affecting librechat. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.

LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address.

Why this priority

High severity
Public exploit reference

No fix is published yet: follow the downgrade or mitigation steps.

Risk facts

CVSS score	7.7 (High)
Attack vector	Network (remote)
Attack complexity	Low
Privileges needed	Low
User interaction	None
EPSS exploit chance	0.3% (top 83%)
CISA exploited list	No
Weakness	CWE-918
Published	2026-03-27
Last modified	2026-10-26

Publisher (CNA): GitHub, Inc. · Vendor: librechat

Last updated 2026-10-26 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score

Am I affected?

Timeline

2026-03-27 20:16 UTCPublished CVE record published
2026-10-26 21:10 UTCUpdated Record last modified

librechat librechat DOWNGRADE

Affected: 0.8.2 · 0.8.2 rc2 · 0.8.2 rc3

Fixed in: no fixed release known

Safe to downgrade to: a release before 0.8.2

1. Check installed version

apt-cache policy librechat || rpm -q librechat || librechat --version

2. No fixed release: DOWNGRADE to a release before 0.8.2 (Debian / Ubuntu)

apt-cache madison librechat sudo apt install librechat=<VERSION_BEFORE_0.8.2> sudo apt-mark hold librechat

2. No fixed release: DOWNGRADE (RHEL / Amazon Linux / Fedora)

dnf --showduplicates list librechat sudo dnf downgrade librechat-<VERSION_BEFORE_0.8.2> sudo dnf versionlock add librechat

Downgrade risk

Downgrading can break dependent software and may reopen older bugs. Read the distro advisory first and test on a non-production host.

After downgrade

Restart the service, and keep the package held until a fixed release ships.

Verify at the official source NVD · CVE Program · Report a problem with this page
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.

Quick answers

How do I fix CVE-2026-31945?

librechat: downgrade or apply the listed mitigation. Exact commands for each OS are on this page.

Is CVE-2026-31945 being exploited?

CVE-2026-31945 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.

What does CVE-2026-31945 affect?

CVE-2026-31945 affects librechat. Severity is high (CVSS 7.7). LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.co

How urgent is CVE-2026-31945?

Priority 36/100. High severity; Public exploit reference

Software pages

GitHub vulnerabilities · OpenAI ChatGPT vulnerabilities

Related CVEs

CVE-2026-31943 HIGH 8.5 UPGRADE LibreChat is a ChatGPT clone with additional features
CVE-2026-31951 MEDIUM 6.8 UPGRADE LibreChat is a ChatGPT clone with additional features
CVE-2026-31950 MEDIUM 5.3 DOWNGRADE LibreChat is a ChatGPT clone with additional features
CVE-2026-54033 HIGH 7.7 UPGRADE LibreChat is an enhanced ChatGPT clone that supports multiple AI providers
CVE-2026-54037 MEDIUM 6.5 UPGRADE LibreChat is an enhanced ChatGPT clone that supports multiple AI providers

References

← Back to latest CVEs