Evidence used
- No CISA KEV confirmation is currently recorded.
- The selected CVSS metric records a network-reachable, unauthenticated path with no user interaction.
- EPSS is 0.69% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2026
CVE-2025-66455High confidence
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
InternLM · lmdeploy
Official source article: GitHub GHSA-2VH9-42VM-XMV2 ↗. Check the applicable product and release in the original source.
9.8CriticalCVSS 3.1
Within 72 hours
Fix not verifiedCritical technical impact with a remotely reachable, unauthenticated path; no CISA KEV confirmation is currently recorded.
R
Open reassessment dashboard →Operational reassessment
Published severity in operational context
Published severityCritical→Operational priority:Critical, unchanged from published severity.unchanged
Compensating controls
- Restrict the affected network interface to trusted sources where business-safe.
- Monitor vendor guidance and exploitation sources for a material change.
Verification
- Confirm that the asset runs InternLM lmdeploy and falls inside the recorded affected range.
- Recheck the vendor advisory before scheduling a change because no verified fixed version is currently retained.
- Validate exposure, authentication requirements and compensating controls in the actual environment.
- Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Open-source package ranges3 source-attributed ranges
These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.
| Ecosystem and package | Affected range | First fixed version | Evidence |
|---|---|---|---|
| PyPIlmdeploy | ECOSYSTEM: introduced 0.9.2; fixed 0.16.0 | 0.16.0 | OSV record ↗aggregator derived · 1 Oct 2026 |
| PyPIlmdeploy | ECOSYSTEM: introduced 0.9.2; fixed 0.16.0 | 0.16.0 | OSV record ↗source linked ecosystem record · 1 Oct 2026 |
| piplmdeploy | >= 0.9.2, < 0.16.0 | 0.16.0 | GitHub advisory ↗upstream repository advisory · 21 Sep 2026 |
Critical technical impact with a remotely reachable, unauthenticated path; no CISA KEV confirmation is currently recorded.
Fix not verified01
What, why and how
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 `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.
What
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 `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.
Why
Attacker-influenced serialised data is reconstructed as trusted objects, which can invoke dangerous application behaviour.
How
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may execute code or commands in the affected security context.
What
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 `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.
Why
Attacker-influenced serialised data is reconstructed as trusted objects, which can invoke dangerous application behaviour.
How
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may execute code or commands in the affected security context.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation No confirmed evidence
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material None recorded
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
- Likely attack path
- a network path → Deserialization of Untrusted Data → execute code or commands in the affected security context
- Attack surface
- Network
- Privileges required
- None: unauthenticated exploitation is possible
- User interaction
- None
- Attack complexity
- Low: no specialised conditions are recorded
- Security boundary
- Unchanged: impact remains within the vulnerable component's security authority
- Weakness
?
CWE means Common Weakness Enumeration: a standard category for the underlying weakness. - CWE-502 ↗
CWE-502: Deserialization of Untrusted Data. The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
- CVSS vector
?
CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity. CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HCommon Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRNonePrivileges required: The attacker does not need an account or existing privileges.UINoneUser interaction: No action by another user is required.SUnchangedScope: The security impact remains within the vulnerable component's authority.CHighConfidentiality impact: A successful attack can cause a major loss.IHighIntegrity impact: A successful attack can cause a major loss.AHighAvailability impact: A successful attack can cause a major loss.- Post-exploitation / living off the land
- After compromise, an attacker may use built-in shells, scripting engines, scheduled tasks and native network utilities for discovery, persistence or movement. This is a plausible LoTL path, not evidence that it has occurred for every attack.
03
Patch and workaround
Operational remediation based on structured source evidence.
- Status
?
Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change. - Fix not verified
- Affected
- lmdeploy: >= 0.9.2, < 0.16.0
- Fixed
- No fixed version is explicitly recorded in the structured CVE data.
- Action
- No verified patch reference is present in the current structured sources. Check the vendor advisory before making a change.
- Workaround
- No verified workaround is recorded. If business-safe, reduce exposure to the affected interface and allow only trusted sources until authoritative guidance is available.
04
Evidence and provenance
Published 18 Sept 2026 · Last source change 18 Sept 2026, 19:54 UTC · CWE-502 · Deserialization of Untrusted Data
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-09-19
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2025-210969
Product sourceCNA
Remediation sourceCVE/CNA references
CWE sourceCNA
NVD statusNVD awaiting enrichment
Core structured fields are present and their contributing authorities are shown above.
Material change intelligence
View recent updates ↗What changed after publication
- ENISA EUVD mappingEUVD-2025-210969 was added to the official ENISA EUVD mapping for this CVE.ENISA EUVD ↗
- Before
- not recorded
- After
- {"euvdId":"EUVD-2025-210969"}
- Catalogue recordCVE added to the BlackTree catalogue.CNA ↗
Technical terms and abbreviations used in this report
- CVE
- Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
- CVSS
- Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
- EPSS
- Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
- CWE
- Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
- CNA
- CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
- CISA ADP
- Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
- NVD
- National Vulnerability Database: NIST's enrichment service for CVE records.
- CERT / CSIRT
- A computer security incident response team that publishes warnings or coordinates incident response.
- PoC
- Proof of concept: public material that demonstrates or helps reproduce exploitation.
- CSAF
- Common Security Advisory Framework: a machine-readable format for security advisories.
- LoTL
- Living off the land: abuse of legitimate tools or system functions during an attack.