Cyber Resilience

CVE-2026-44654

MediumPublic PoCUpdated

Published: 02 June 2026

Published
02 June 2026
Modified
17 June 2026
KEV Added
Patch
CVSS Score v4 5.7 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0027 17.9th percentile
Risk Priority 35 floored blend · peak EPSS

Summary

CVE-2026-44654 is a medium-severity Incorrect Authorization (CWE-863) vulnerability in Librechat Librechat. Its CVSS base score is 5.7 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Data Destruction (T1485); ranked at the 17.9th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as LLM Application Platforms; in the Data-Related Vulnerabilities risk domain.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability details

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
LLM Application Platforms
Risk Domain
Data-Related Vulnerabilities
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ai, chatgpt, librechat

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1485 Data Destruction Impact
Adversaries may destroy data and files on specific systems or in large numbers on a network to interrupt availability to systems, services, and network resources.
Why these techniques?

CWE-863 authz flaw directly enables unauthorized global file deletion (T1485) across agents.

Confidence: MEDIUM · MITRE ATT&CK Enterprise v19.0

Affected Assets

librechat
librechat
≤ 0.8.5

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

addresses: CWE-863

Periodic review and update of procedures reduces incorrect authorization implementations over time.

addresses: CWE-863

Supervision identifies cases where authorization logic incorrectly permits unauthorized actions.

addresses: CWE-863

Defining permitted attribute values and auditing modifications reduces the chance of incorrect authorization outcomes due to tampered or missing labels.

addresses: CWE-863

The authorization process and usage restrictions help prevent incorrect authorization for remote access types.

addresses: CWE-863

Establishing configuration and connection requirements helps ensure correct rather than incorrect authorization for wireless access.

addresses: CWE-863

Establishing connection authorization processes for mobile devices helps ensure authorization decisions are correctly implemented rather than incorrect.

addresses: CWE-863

Monitoring account use, notifying on changes, and reviewing accounts for compliance corrects incorrect authorization assignments.

addresses: CWE-863

Ensures authorization decisions for external system use are correctly implemented and enforced.

References