CVE-2026-103395: Deserialization of Untrusted Data in ModelTC LightLLM
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account privileges.
CVE-2026-103395: Deserialization of Untrusted Data in ModelTC LightLLM
Description
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account 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.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-09-30T14:28:17.072Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6abd25252a4e24523d2793e6
Added to database: 09/30/2026, 15:05:09 UTC
Last updated: 09/30/2026, 15:05:09 UTC
Views: 1
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
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.