CVE Intelligence
Critical Insecure deserialization

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 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.

Published Aug 19, 2026 · Updated Oct 15, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulnCheck

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • Technical severity (critical)+10
  • CISA SSVC: exploitation "poc"+5
  • Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
—
No EPSS score.
Affects
Internlm
Lmdeploy
CVSS base
9.8
Critical · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
Yes
can an attacker script the kill-chain steps
Technical impact
Total
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Internlm Lmdeploy).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. No fix documented in the sources: reduce exposure and monitor the vendor advisory.
  4. Search available logs for exploit probes matching the vulnerability class (insecure deserialization), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Internlm Lmdeploy ≥ 0.9.2 and < 0.16.0 Vulnerable CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
9.3 CVSS 4.0 Critical — — disclosure@vulncheck.com via NIST National Vulnerability Database
9.3 CVSS 4.0 Critical — — VulnCheck via CVE Program (cve.org) e CISA ADP
9.8 CVSS 3.1 Critical 3.9 5.9 disclosure@vulncheck.com via NIST National Vulnerability Database
9.8 CVSS 3.1 Critical — — VulnCheck via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: disclosure@vulncheck.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-502 · Deserialization of Untrusted Data

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Monitor serialized objects in requests and unexpected processes spawned by the runtime.
web/proxy/WAF logsnetwork IDS/IPSendpoint telemetry (EDR)application logs

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · internlm/lmdeploy
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 15, 2026
  • CVSS changed · 9.8
    Oct 15, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 15, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 15, 2026 · NIST National Vulnerability Database
  • CVE published
    Aug 19, 2026 · VulnCheck

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 15, 2026 – Oct 15, 2026

References

7 on the record

Elsewhere on this site

Internlm
every CVE for this vendor
Insecure deserialization
same class
CWE-502
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-33625 LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading 27d
  • CVE-2025-66455 LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py 27d
  • CVE-2026-92983 InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch 28d
  • CVE-2026-92971 InternLM LMDeploy through 0.17.0 Assertion Denial of Service 28d
  • CVE-2025-59953 LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy 29d
  • CVE-2026-63764 LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass Jul 21, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No FIRST EPSS score.
  • No fixed version, patch or mitigation documented.
  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-76850 is "LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector", rated Critical. It affects Lmdeploy (Internlm); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.8 describes technical severity. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.