CVE-2025-67729High· 8.8▾ TwilightLMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading m…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 48.4 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Jul 31.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.5%
0.5% → 0.6%
Last analysed / modified upstream
LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1.
lmdeploy < 0.11.1Upgrade past the affected range:
lmdeploy 0.11.1Affected packages:
lmdeploy < 0.11.1Patched in:
lmdeploy 0.11.1Connected by shared product, vendor, weakness, or advisory.
CVE-2025-66455Critical· 9.8LMDeploy is a toolkit for compressing, deploying, and serving large language models
CVE-2025-59953Critical· 9.8LMDeploy is a toolkit for compressing, deploying, and serving large language models
CVE-2026-76850Critical· 9.8LMDeploy deserializes disaggregated-serving peer messages with pickle
GHSA-39wr-7q6h-cf68High· 7.5LMDeploy has an SSRF bypass
CVE-2026-33625High· 8.8LMDeploy is a toolkit for compressing, deploying, and serving large language models
CVE-2026-46432High· 7.8LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization