CVE-2026-76850

Published: Ago 20, 2026 Last Modified: Ago 20, 2026
ExploitDB:
Other exploit source:
Google Dorks:
CRITICAL 9,3
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
CRITICAL 9,8
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Scope: unchanged
Confidentiality: high
Integrity: high
Availability: high

Description

AI Translation Available

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.

EPSS (Exploit Prediction Scoring System)

Trend Analysis

EPSS (Exploit Prediction Scoring System)

Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.

EPSS Score
0,0098
Percentile
0,6th
Updated

Single Data Point

Only one EPSS measurement is available for this CVE. Trend analysis requires multiple data points over time.

502

Deserialization of Untrusted Data

Draft
Common Consequences
Security Scopes Affected:
Integrity Availability Other
Potential Impacts:
Modify Application Data Unexpected State Dos: Resource Consumption (Cpu) Varies By Context
Applicable Platforms
Languages: Java, Ruby, PHP, Python, JavaScript
Technologies: Not Technology-Specific, ICS/OT, AI/ML
View CWE Details
https://github.com/InternLM/lmdeploy/issues/4804
https://github.com/InternLM/lmdeploy
https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/…
https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/…
https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99…
https://github.com/InternLM/lmdeploy/issues/4804
https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0
https://www.vulncheck.com/advisories/lmdeploy-remote-code-execution-via-unsafe-…