CVE-2026-119706
InternLM LMDeploy 0.9.0 through 0.18.0 contains an unauthenticated …
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.
High priority: this vulnerability is rated critical and can be attacked over the network without a login.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/InternLM/lmdeploy
- github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/serve/openai/endpoints/management.py#L5
- github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/turbomind/turbomind.py#L345
- github.com/InternLM/lmdeploy/issues/4698
- github.com/InternLM/lmdeploy/pull/4964
- www.vulncheck.com/advisories/lmdeploy-0.9.0-through-0.18.0-unauthenticated-rce-via-update-
- nvd.nist.gov/vuln/detail/CVE-2026-119706
- cve.org/CVERecord?id=CVE-2026-119706
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.