CVE-2026-103395
9.8 CRITICALpublic exploit availablePublished 2026-09-30 · Updated 2026-09-30
AI risk analysis
- Summary
- LightLLM through 1.2.0 allows unauthenticated attackers to execute arbitrary code via a deserialization vulnerability in the remote_infer_images method with allow_pickle enabled.
- Exploitability
- Exploitation is relatively straightforward given the unauthenticated nature and the availability of a known vulnerable endpoint.
- Blast radius
- If exploited, this could result in full compromise of the service account with potential lateral movement within the network.
- Detection
- No reliable host or network indicator is derivable from the published description.
- Prioritized remediation
- Upgrade to LightLLM 1.2.1 or later.
rceunauthpickleservice
Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.
NVD 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 vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-502
Public exploit & PoC references
- https://github.com/ModelTC/LightLLM
- https://github.com/ModelTC/LightLLM/issues/1610
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L11
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py#L138-L140
- https://github.com/ModelTC/LightLLM/issues/1610
All references
- https://github.com/ModelTC/LightLLM
- https://github.com/ModelTC/LightLLM/issues/1610
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L11
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py#L138-L140
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-visual-only-rpyc-service
- https://github.com/ModelTC/LightLLM/issues/1610
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- CRITICALCVE-2025-66455PoC
- HIGHCVE-2026-100841PoC
- HIGHCVE-2026-100843PoC
- HIGHCVE-2026-100846PoC
- HIGHCVE-2026-18490
- HIGHCVE-2026-28325
- CRITICALCVE-2026-76750
- HIGHCVE-2026-76834PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.