CVE-2026-90919: Deserialization of Untrusted Data in ModelTC LightLLM
LightLLM versions up to 1.2.0 have a critical remote code execution vulnerability in the Config Server's unauthenticated /visual_register WebSocket endpoint. This endpoint directly deserializes the first client frame using pickle.loads(), allowing attackers who can reach the Config Server port to send malicious serialized payloads that execute arbitrary code with the Config Server's privileges.
AI Analysis
Technical Summary
CVE-2026-90919 describes a remote code execution vulnerability in ModelTC's LightLLM product through version 1.2.0. The vulnerability exists in the Config Server component, specifically in the unauthenticated /visual_register WebSocket endpoint. This endpoint passes the first client frame directly to Python's pickle.loads() function without validation, enabling attackers to craft malicious serialized payloads containing a __reduce__ method. When deserialized, these payloads execute arbitrary code with the privileges of the Config Server process. The CVSS 4.0 base score is 9.3, indicating critical severity with network attack vector, no required privileges or user interaction, and high impact on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation allows remote attackers to execute arbitrary code on the Config Server with its process privileges, potentially leading to full system compromise or unauthorized control over the affected service. The vulnerability is exploitable without authentication and requires only network access to the Config Server port.
Mitigation Recommendations
No patch or official fix information is provided in the available data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict network access to the Config Server port to trusted sources only to prevent unauthorized exploitation.
CVE-2026-90919: Deserialization of Untrusted Data in ModelTC LightLLM
Description
LightLLM versions up to 1.2.0 have a critical remote code execution vulnerability in the Config Server's unauthenticated /visual_register WebSocket endpoint. This endpoint directly deserializes the first client frame using pickle.loads(), allowing attackers who can reach the Config Server port to send malicious serialized payloads that execute arbitrary code with the Config Server's privileges.
CVSS v4.0
Score 9.3critical
Affected software
ModelTC
LightLLM
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-90919 describes a remote code execution vulnerability in ModelTC's LightLLM product through version 1.2.0. The vulnerability exists in the Config Server component, specifically in the unauthenticated /visual_register WebSocket endpoint. This endpoint passes the first client frame directly to Python's pickle.loads() function without validation, enabling attackers to craft malicious serialized payloads containing a __reduce__ method. When deserialized, these payloads execute arbitrary code with the privileges of the Config Server process. The CVSS 4.0 base score is 9.3, indicating critical severity with network attack vector, no required privileges or user interaction, and high impact on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation allows remote attackers to execute arbitrary code on the Config Server with its process privileges, potentially leading to full system compromise or unauthorized control over the affected service. The vulnerability is exploitable without authentication and requires only network access to the Config Server port.
Mitigation Recommendations
No patch or official fix information is provided in the available data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict network access to the Config Server port to trusted sources only to prevent unauthorized exploitation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-09-14T11:04:23.742Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6aa7ded355bf5e2cf5006f2b
Added to database: 09/14/2026, 11:47:31 UTC
Last enriched: 09/14/2026, 12:01:31 UTC
Last updated: 09/14/2026, 12:26:53 UTC
Views: 21
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.