CriticalCVE-2026-76850

    InternLM LMDeploy: Deserialization of Untrusted Data (CVE-2026-76850)

    Published Last modified Sources: CVE.org

    What is affected, what to do

    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.

    Update InternLM LMDeploy to version 0.16.0.

    Affected
    • InternLM LMDeploy lt 0.9.2..0.16.0
    Fixed in
    • InternLM LMDeploy 0.16.0

    Not sure whether and how you are affected? Ask a question about this vulnerability

    Metrics

    9.8

    Priority

    XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

    Source: NVD, CVSS v3

    9.8

    CVSS v3

    Severity Critical on the scale from 0 to 10.

    Source: CVE.org

    1.3 %

    EPSS score

    Moderate — model estimates 1-10% exploitation likelihood.

    Source: FIRST EPSS, percentile 69.9

    Show all metrics
    Severity
    Critical
    Priority (0–325)

    The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first?

    Read in glossary
    111.49 Methodology
    Exploit maturity

    An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack.

    Read in glossary
    no public PoC known
    XIEM Effective CVSS

    XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command.

    Read in glossary
    9.8 Methodology
    CVSS v3

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    9.8
    CVSS v4

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    9.3
    EPSS score

    The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“.

    Read in glossary
    1.3 %
    Moderate — model estimates 1-10% exploitation likelihood.
    EPSS percentile

    The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking.

    Read in glossary
    69.9
    High — this CVE ranks above the median of all CVEs scored today (rank ≥ 36%).
    KEV status

    The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching.

    Read in glossary
    —
    Published
    CISA assessment (SSVC)
    Exploitation: proof of concept · automatable · Technical impact: total
    Source: CISA Vulnrichment, as of 20 August 2026
    CWE

    CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect.

    Read in glossary
    CWE-502

    Detection rules

    No NEOSEC detection rule is available for this vulnerability yet.

    Classification under NIS2 and CRA

    Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

    NIS2

    NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management.

    Read in glossary
    High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
    CRA

    The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates.

    Read in glossary
    From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
    ISO/IEC 27001

    ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security.

    Read in glossary
    Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

    Description

    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.

    Source: cvelistv5, NVD (NIST)

    Affected products

    The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

    Affected products
    Affected versionsFixed in
    InternLMlmdeploy
    • 0.9.2 – < 0.16.0
    • 0.16.0

    Vendors and products

    Weakness classes (CWE)

    • CWE-502Deserialization of Untrusted Data

      Base

      The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.

      Entry at MITRE CWE-502

    References & sources

    • github.comGitHub Issue #4804Issue tracking
    • github.comfix(disagg): use JSON instead of pickle for P2P ZMQ requestsPatch
    • github.comVulnerable recv_pyobj() call in v0.15.0Technical description
    • github.comCaller-controlled zmq_address passed to connect() in v0.15.0Technical description
    • github.comlmdeploy v0.16.0Release notes
    • github.comInternLM/lmdeployProduct
    • vulncheck.comVulnCheck Advisory: LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer ConnectorThird-party advisory

    Changes to this CVE

    Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

    1. Record modifiedCISA ADP

      CISA assessment (SSVC): exploitation: proof of concept, automatable: yes

      Show 2 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/issues/4804
      SSVC assessmentadded
      —
      {"id":"CVE-2026-76850","role":"CISA Coordinator","options":[{"exploitation":"poc"},{"automatable":"yes"},{"technicalImpact":"total"}],"version":"2.0.3","timestamp":"2026-08-20T14:08:23.395015Z"}

      Source identifier: 134c704f-9b21-4f2e-91b3-4a467353bcc0

    2. ReceivedVulnCheck

      CVSS V4.0: AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

      CVSS V3.1: AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

      Weakness type: CWE-502

      Description added or changed

      Show 12 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Affected versions (publisher)added
      —
      lmdeploy
      Descriptionadded
      —
      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.
      CVSSadded
      —
      AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
      CVSSadded
      —
      AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
      Weakness type (CWE)added
      —
      CWE-502
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L61
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L79
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/issues/4804
      Referenceadded
      —
      https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0
      Referenceadded
      —
      https://www.vulncheck.com/advisories/lmdeploy-remote-code-execution-via-unsafe-pickle-deserialization-in-the-disaggregated-serving-peer-connector

      Source identifier: disclosure@vulncheck.com

    Embed badge

    Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

    Badge preview for CVE-2026-76850
    <a href="https://intel.neosec.eu/en/cve/CVE-2026-76850"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-76850.svg?lang=en" alt="CVE-2026-76850 – NEOSEC Intel" height="20"></a>