CVE-2026-103040: Deserialization of Untrusted Data in ModelTC LightLLM
LightLLM versions up to 1.2.0 have a critical remote code execution vulnerability in the router profiler service when started with the --enable_profiling flag. This service runs an unauthenticated RPyC server that uses pickle deserialization, allowing attackers to execute arbitrary code by sending crafted serialized objects.
AI Analysis
Technical Summary
CVE-2026-103040 describes a remote code execution vulnerability in ModelTC's LightLLM product up to version 1.2.0. The vulnerability exists in the router profiler service when launched with the --enable_profiling flag enabled. This service exposes an unauthenticated RPyC server that performs pickle deserialization on incoming data. Because pickle deserialization is inherently unsafe with untrusted input, attackers can send malicious serialized objects to the profiler command queue, resulting in arbitrary code execution on the affected system.
Potential Impact
An unauthenticated remote attacker can execute arbitrary code on systems running LightLLM up to version 1.2.0 with the router profiler service started using the --enable_profiling flag. This can lead to full system compromise without requiring any privileges or user interaction.
Mitigation Recommendations
No patch or official fix information is provided. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, avoid starting the router profiler service with the --enable_profiling flag or restrict network access to the service to trusted users only.
CVE-2026-103040: Deserialization of Untrusted Data in ModelTC LightLLM
Description
LightLLM versions up to 1.2.0 have a critical remote code execution vulnerability in the router profiler service when started with the --enable_profiling flag. This service runs an unauthenticated RPyC server that uses pickle deserialization, allowing attackers to execute arbitrary code by sending crafted serialized objects.
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-2026-103040 describes a remote code execution vulnerability in ModelTC's LightLLM product up to version 1.2.0. The vulnerability exists in the router profiler service when launched with the --enable_profiling flag enabled. This service exposes an unauthenticated RPyC server that performs pickle deserialization on incoming data. Because pickle deserialization is inherently unsafe with untrusted input, attackers can send malicious serialized objects to the profiler command queue, resulting in arbitrary code execution on the affected system.
Potential Impact
An unauthenticated remote attacker can execute arbitrary code on systems running LightLLM up to version 1.2.0 with the router profiler service started using the --enable_profiling flag. This can lead to full system compromise without requiring any privileges or user interaction.
Mitigation Recommendations
No patch or official fix information is provided. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, avoid starting the router profiler service with the --enable_profiling flag or restrict network access to the service to trusted users only.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-09-29T22:16:59.567Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6abc4489680226ef6869e5b6
Added to database: 09/29/2026, 23:06:49 UTC
Last enriched: 09/29/2026, 23:21:24 UTC
Last updated: 09/29/2026, 23:49:11 UTC
Views: 5
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.