CVE-2026-26220: CWE-502 Deserialization of Untrusted Data in ModelTC LightLLM
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.
AI Analysis
Technical Summary
CVE-2026-26220 is a critical vulnerability in ModelTC's LightLLM product, affecting version 1.1.0 and prior. The vulnerability arises from unsafe deserialization of untrusted data via Python's pickle.loads() function in the PD master node's WebSocket endpoints. Because there is no authentication or validation on incoming binary frames, a remote attacker with network access to the PD master node can send malicious serialized data to execute arbitrary code remotely. This vulnerability is classified under CWE-502 (Deserialization of Untrusted Data) and has a CVSS 4.0 base score of 9.3, indicating high impact and ease of exploitation.
Potential Impact
Successful exploitation results in unauthenticated remote code execution on the PD master node of LightLLM. This can lead to full system compromise, data breach, or disruption of service. The vulnerability requires network access to the PD master node but no privileges or user interaction. The CVSS 4.0 vector indicates no attack complexity, no privileges required, and no user interaction needed, with high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict network access to the PD master node to trusted entities only to prevent unauthorized access to the vulnerable WebSocket endpoints. Monitor for unusual activity targeting these endpoints. Do not expose the PD master node to untrusted networks.
CVE-2026-26220: CWE-502 Deserialization of Untrusted Data in ModelTC LightLLM
Description
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.
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.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-26220 is a critical vulnerability in ModelTC's LightLLM product, affecting version 1.1.0 and prior. The vulnerability arises from unsafe deserialization of untrusted data via Python's pickle.loads() function in the PD master node's WebSocket endpoints. Because there is no authentication or validation on incoming binary frames, a remote attacker with network access to the PD master node can send malicious serialized data to execute arbitrary code remotely. This vulnerability is classified under CWE-502 (Deserialization of Untrusted Data) and has a CVSS 4.0 base score of 9.3, indicating high impact and ease of exploitation.
Potential Impact
Successful exploitation results in unauthenticated remote code execution on the PD master node of LightLLM. This can lead to full system compromise, data breach, or disruption of service. The vulnerability requires network access to the PD master node but no privileges or user interaction. The CVSS 4.0 vector indicates no attack complexity, no privileges required, and no user interaction needed, with high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict network access to the PD master node to trusted entities only to prevent unauthorized access to the vulnerable WebSocket endpoints. Monitor for unusual activity targeting these endpoints. Do not expose the PD master node to untrusted networks.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-02-11T20:08:07.944Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6994257080d747be207b7270
Added to database: 02/17/2026, 08:23:12 UTC
Last enriched: 07/15/2026, 11:09:03 UTC
Last updated: 09/10/2026, 22:08:42 UTC
Views: 331
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.