Deserialization in Modeltc Lightllm
CVE-2026-103395
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.
Vulnerability class: Insecure Deserialization
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.006, 50.1th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
Weakness classification (CWE)
References
- GitHub Issue #1610 (issue-tracking)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py (technical-description)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_onl… (technical-description)
- github.com/ModelTC/LightLLM (product)
- VulnCheck Advisory: LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service (third-party-advisory)