120 matches found
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 — Лаборатория SSRF для Vision-Language в LMDeploy Обзор Этот репозиторий воспроизводит CVE-2026-33626 – уязвимость подделки серверных запросов SSRF в пути загрузки изображений для vision-language в LMDeploy. Уязвимое поведение возникает, когда LMDeploy получает URL изображения, а...
CVE-2026-33625
creationtimestamp| type| source ---|---|--- 2026-09-18 18:35:22+00:00| published-proof-of-concept| https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr 2026-09-22 11:40:56+00:00| seen| https://mastodon.social/users/hugovalters/statuses/117314502130222385 2026-09-22...
CVE-2026-33625
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model wit...
CVE-2025-66455
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recvpyobj to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements...
EUVD-2026-83202
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model wit...
CVE-2026-33625 LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model wit...
CVE-2026-33625
LMDeploy versions 0.12.1 through 0.12.2 contain a code injection vulnerability in lmdeploy/pytorch/config.py (line 620). The quant_dtype value from a model's HuggingFace quantization_config is passed to eval(f'torch.{quant_dtype}') without validation, enabling an attacker who publishes a maliciou...
CVE-2026-33625 LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model wit...
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
Summary lmdeploy = latest contains a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted quantizationconfig.quantdtype value. When a user loads the model with...
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
Summary LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recvpyobj to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements recvpyobj using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used...
CVE-2025-66455 LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recvpyobj to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements...
CVE-2025-66455 LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recvpyobj to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements...
EUVD-2025-210969
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recvpyobj to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements...
CVE-2025-66455
LMDeploy versions 0.9.2 through 0.15.x are vulnerable to unauthenticated remote code execution (CVSS 9.8 Critical ) in its PyTorch DistServe/PD-disaggregation control plane. The root cause is that recv_pyobj() in EngineP2PConnection.handle_zmq_recv() performs pickle deserialization on messages re...
CVE-2026-92983
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate...
CVE-2026-92983 InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate...
CVE-2026-92983
InternLM LMDeploy through 0.17.0 is affected by a memory exhaustion vulnerability in its DistServe prefill/decode disaggregation mode . The root cause is that the proxy uses user-facing session IDs instead of internal scheduler keys, causing scheduler sessions to never be released. An unauthentic...
EUVD-2026-81620
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate...
CVE-2026-92983 InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate...