CVE-2025-59953

creationtimestamp| type| source ---|---|--- 2026-09-16 16:35:02+00:00| published-proof-of-concept| https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw 2026-09-16 17:20:31+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/cfid76vzr44xo 2026-09-16 18:07:47+00:00|...

CVE-2025-59953

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server AsyncRPCServer in zmqrpc.py for supporting the RPC communications. In its core functionality callandresponse, I found i...

CVE-2025-59953

LMDeploy (by InternLM ), a toolkit for compressing, deploying, and serving large language models, is affected by a remote code execution vulnerability in versions 0.9.1 through 0.10.1 . The root cause lies in the AsyncRPCServer component (zmq_rpc.py), where the call_and_response() function direct...

EUVD-2025-210921

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server AsyncRPCServer in zmqrpc.py for supporting the RPC communications. In its core functionality callandresponse, I found i...

CVE-2025-59953 LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server AsyncRPCServer in zmqrpc.py for supporting the RPC communications. In its core functionality callandresponse, I found i...

LMDeploy - Server-Side Request Forgery

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery SSRF vulnerability in the vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal or...

CVE-2026-33626-Lab

CVE-2026-33626 — LMDeploy 视觉语言 SSRF 实验环境 概述 本仓库重现了 CVE-2026-33626 ，即 LMDeploy 视觉语言图像加载路径中的服务器端请求伪造（SSRF）漏洞。 漏洞行为发生在 LMDeploy 接收图像 URL 时，服务器端图像加载器在不正确阻止内部、私有、回环或链路本地地址的情况下直接获取该 URL。 本实验环境对比： 服务| 版本| 用途 ---|---|--- vuln| LMDeploy 0.12.0| 展示存在漏洞的行为 patched| LMDeploy 0.12.3| 展示修复后的行为 internal| 本地金丝雀服...

EUVD-2026-62972

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handlezmqrecv coroutine in lmdeploy/pytorch/disagg/conn/engineconn.py reads peer-to-peer cache-free requests with recvpyobj, which deserializes the received bytes with pickle.loads, and the isinstance check against...

CVE-2026-76850

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handlezmqrecv coroutine in lmdeploy/pytorch/disagg/conn/engineconn.py reads peer-to-peer cache-free requests with recvpyobj, which deserializes the received bytes with pickle.loads, and the isinstance check against...

CVE-2026-76850 LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handlezmqrecv coroutine in lmdeploy/pytorch/disagg/conn/engineconn.py reads peer-to-peer cache-free requests with recvpyobj, which deserializes the received bytes with pickle.loads, and the isinstance check against...

CVE-2026-76850

LMDeploy (InternLM) is vulnerable to remote code execution via unsafe pickle deserialization in its disaggregated-serving peer connector. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py deserializes peer-to-peer messages with pickle.loads() before any type validation,...

CVE-2026-76850 LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handlezmqrecv coroutine in lmdeploy/pytorch/disagg/conn/engineconn.py reads peer-to-peer cache-free requests with recvpyobj, which deserializes the received bytes with pickle.loads, and the isinstance check against...

CVE-2026-76850 LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handlezmqrecv coroutine in lmdeploy/pytorch/disagg/conn/engineconn.py reads peer-to-peer cache-free requests with recvpyobj, which deserializes the received bytes with pickle.loads, and the isinstance check against...

CVE-2026-63764

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...

CVE-2026-63764 LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...

CVE-2026-63764

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...

CVE-2026-63764 LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...

CVE-2026-63764

LMDeploy prior to 0.14.0 contains a server-side request forgery (SSRF) in the _load_http_url function of the media handler. The private-IP guard validates only the original URL; after HTTP redirects, hosts are not re-validated. An unauthenticated attacker can submit a crafted image_url to the cha...

PT-2026-62099

lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image url that redirects to internal targets. Attackers can send a POST request to the...

PYSEC-2026-2608 lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "getmodelarch and related helpers hardcode trustremotecode=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this repor...