CVE Tools
Track your stack

CVE-2026-44654

LibreChat: Shared-agent editor can globally delete owner's file records — breaks owner's other private agents

No known exploitation. EPSS puts it in the 33rd percentile. Fixed in 0.8.5.

CVSS 3.18.1HighEPSS percentile33rd0.4% chance in 30 daysCISA KEVNot listedNo confirmed exploitation
No public exploit knownFix0.8.5Upgrade to this build

Published Updated Sources: CVE.org, NVD

NVD CVE.org

What to do

Find your product and version, then upgrade to the build on the right.

  • danny-avila LibreChatAffected: < 0.8.5Upgrade to: not statedStated by: CVE record
  • LibrechatAffected: < 0.8.5Upgrade to: 0.8.5Stated by: NVD

Versions as the sources state them. Full version matrix after sign-in

Is your organisation exposed?Request an assessment to establish which checks fit your systems.

What it is

From the CVE record

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, a shared-agent editor can delete file records through `DELETE /api/files` that the owner has reused across multiple agents. The deletion removes the file globally — not just from the shared agent — breaking the owner's other private agents that reference the same `file_id`. The private agent retains a stale `file_id` reference that no longer resolves. A shared-agent editor can destroy files that the owner uses across multiple agents. The owner's private agents — which the attacker has no access to — break silently with stale `file_id` references. This is a cross-agent integrity violation: editing access to one agent should not affect another. Version 0.8.4 contains a patch.

In plain language

No plain-language summary for this CVE yet.

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS33rd
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.4% chance of exploitation activity in the next 30 days, which ranks it in the 33rd percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

7 events over 49 days, from the signal feeds we watch.

  1. Patch availablerecord updated
  2. Patch availablerecord updated
  3. Publishedweakness classified, att&ck mapped

Affected products

Technical detail

CVSS 3.1 vector

Open in the CVSS calculator

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

Scored 8.1 by NVD.

How it is reached

  • Attack Vector NetworkExploitable remotely over the network without any special conditions
  • Attack Complexity LowNo special conditions — the attack can be reliably reproduced
  • Privileges Required LowRequires basic user-level privileges
  • User Interaction NoneNo user interaction needed — fully automated exploitation

Scope

  • Scope UnchangedImpact is limited to the vulnerable component itself

Impact if exploited

  • Confidentiality NoneNo confidentiality impact
  • Integrity HighTotal loss of integrity — attacker can modify any data in the component
  • Availability HighTotal denial of service — the component is completely unavailable

Weaknesses

ATT&CK techniques

Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.

Sources

References in the record

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for LibreChat, not every advisory.