CyberSecBulletin
CVE-2026-76850NVD status: Deferred

lmdeploy: Deserialization of Untrusted Data

Published Updated By the CyberSecBulletin desk

CVE-2026-76850 is a critical-severity deserialization of untrusted data vulnerability in lmdeploy from InternLM, with a CVSS 3.1 base score of 9.8 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. The record lists version 0.16.0 as the first without the flaw, so updating lmdeploy to that release or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 1.27% chance of exploitation within 30 days, higher than 70% of scored CVEs.

Patch this week

Critical severity: a successful attack would have severe impact.

What to do

  1. Update lmdeploy to 0.16.0 or a later version.
  2. Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.

Affected products and versions

VendorProductAffected versionsFixed in
InternLMlmdeploy0.9.2 up to, but not including, 0.16.00.16.0

Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.

How the severity score breaks down

Attack vector
NetworkCan be exploited remotely over a network, including the internet.
Attack complexity
LowNo special conditions are needed; the attack works reliably.
Privileges required
NoneNo account or login is needed.
User interaction
NoneNo action by a victim is required.
Scope
UnchangedImpact stays within the vulnerable component.
Confidentiality
HighAll data handled by the component can be read.
Integrity
HighData or code can be modified at will.
Availability
HighThe component can be taken down completely.

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (vulncheck.com).

Scoring systemScoreSeverityScored by
CVSS 4.09.3CriticalCNA (vulncheck.com)
CVSS 3.19.8CriticalCNA (vulncheck.com)

Official 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: the CVE record as published by its numbering authority, via NVD and CVE.org.

The underlying weakness: Deserialization of Untrusted Data

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

How developers prevent this class of flaw

  • If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
  • When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
  • Explicitly define a final object() to prevent deserialization.

More Deserialization of Untrusted Data vulnerabilities (CWE-502)

Timeline

  1. CVE record published.
  2. CISA published its SSVC assessment (exploitation: poc, automatable: yes, technical impact: total).
  3. Record last changed materially (score, affected products, status or references).

References

Other vulnerabilities in lmdeploy

All lmdeploy vulnerabilities

Recent Deserialization of Untrusted Data vulnerabilities

Spotted an error? Tell us.