← Back to search

CVE-2026-103040

9.8 CRITICALpublic exploit available

Published 2026-09-29 · Updated 2026-09-29

AI risk analysis

Summary
LightLLM versions through 1.2.0 are vulnerable to remote code execution due to an unauthenticated RPyC server with pickle deserialization enabled, allowing attackers to execute arbitrary code via crafted serialized objects.
Exploitability
Exploitation is relatively straightforward given the unauthenticated nature and the presence of a RPyC server with deserialization enabled. Attackers must start the service with the --enable_profiling flag.
Blast radius
If exploited, this vulnerability could lead to complete compromise of the affected system, potentially allowing attackers to execute arbitrary code and gain full control over the system.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Disable the profiling feature by not starting the service with the --enable_profiling flag, or upgrade to a version later than 1.2.0 if available.
rcepickle-deserializationremote-code-executionunauthenticatedservice-exploit

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 contains a remote code execution vulnerability in the router profiler service when started with --enable_profiling flag. The service exposes an unauthenticated RPyC server with pickle deserialization enabled, allowing attackers to execute arbitrary code by sending crafted serialized objects to the profiler command queue.

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

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.