CVE-2026-103395: ModelTC LightLLM · Deserialization of Untrusted Data
Affects ModelTC LightLLMSource CVE Database V5
Not known to be exploited · CVSS 9.3 Critical.
Data as of 14 Nov 2026, 20:43 UTC
- EPSS
- 0.6% chance of exploitation in 30 days – higher than 50% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 30 Sep 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 14 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| ModelTCLightLLM | Affected
| Fixed in– |
GitHubLightLLMpkg:github/LightLLMOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Until an official fix is available, restrict network access to the visual RPyC port to trusted users only and disable or restrict the use of allow_pickle in the RPyC service configuration if possible.
Description
CVE-2026-103395 is a critical vulnerability in ModelTC LightLLM versions up to 1.2.0. The vulnerability arises from an unauthenticated RPyC service with allow_pickle enabled, which deserializes attacker-controlled data in the remote_infer_images method. This allows remote attackers to execute arbitrary code with service account privileges by passing specially crafted objects.
References
- github.com/ModelTC/LightLLM/issues/1610 (opens in a new tab)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py (opens in a new tab)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py (opens in a new tab)
- github.com/ModelTC/LightLLM (opens in a new tab)
- vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-visual-only-rpyc-service (opens in a new tab)