← CVE Radar
CVE-2026-119706LMDeploy 0.9.0 through 0.18.0 Unauthenticated RCE via /update_weights Pickle Deserialization
InternLM LMDeploy 0.9.0 through 0.18.0 contains an unauthenticated remote code execution vulnerability that allows remote attackers to run OS commands by sending pickled data to the /update_weights endpoint. Attackers can submit a base64-encoded crafted pickle in serialized_named_tensors, which ForkingPickler.loads deserializes without validation, executing commands as the api_server process.
9.3 CRITICALEPSS 1.03%Not in KEVNVD: Deferred
Overview
Severity
| Score | Severity | Version | Vector String |
|---|---|---|---|
| 9.3 | CRITICAL | 4.0VulnCheck (CNA) | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| 9.8 | CRITICAL | 3.1VulnCheck (CNA) | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Details
- CVE ID
- CVE-2026-119706
- Status
- Deferred
- Assigner (CNA)
- VulnCheck
- Published
- Oct 30, 2026
- Last modified
- 2026-11-02 18:29 UTC
- Weaknesses
- CWE-502 · Deserialization of Untrusted Data
Affected Products
As published by the CNA in the CVE record.
InternLMlmdeploy1 version range
- 0.9.0 through 0.18.0
References
- github.com https://github.com/InternLM/lmdeploy
- github.com https://github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/serve/openai/endpoints/management.py#L55-L60
- github.com https://github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/turbomind/turbomind.py#L345
- github.com https://github.com/InternLM/lmdeploy/issues/4698
- github.com https://github.com/InternLM/lmdeploy/pull/4964
- vulncheck.com https://www.vulncheck.com/advisories/lmdeploy-0.9.0-through-0.18.0-unauthenticated-rce-via-update-weights-pickle-deserialization