Deserialization of Untrusted DataWeakness · CWE-502

CVE-2026-26220

CRITICAL · 9.3 CVSS v4.0 Published 2026-02-17
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

LightLLM versions 1.1.0 and prior have an unauthenticated remote code execution vulnerability in PD disaggregation mode. The PD master node exposes WebSocket endpoints that accept binary frames and pass them directly to pickle.loads() without any authentication or input validation, allowing remote attackers to achieve arbitrary code execution by sending crafted malicious pickle payloads.

MitigationRestrict network access to PD master WebSocket endpoints (e.g., firewall rules, network segmentation), implement strong authentication on these endpoints, and replace pickle.loads() with a safe deserialization method (e.g., JSON, MessagePack) or cryptographically signed payloads.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
Authentication
X
User interaction
None
Scope
X

CVSS:4.0/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

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify LightLLM installation and version
    Locate the LightLLM installation directory and check the version file or package metadata. Common methods include: checking pip show lightllm, looking for version.py or __version__ in the installation, or examining setup.py/setup.cfg if source is available.
    Affected if The installed version is 1.1.0 or any prior version (anything <= 1.1.0).
  2. Verify if PD disaggregation mode is enabled
    Examine the LightLLM configuration files and runtime parameters for PD mode settings. Look for configuration keys related to 'pd', 'disaggregation', 'prefill_decode', or 'pd_master' in config files, environment variables, or command-line arguments.
    Affected if PD (prefill-decode) disaggregation mode is configured and active.
  3. Check if WebSocket endpoints are exposed
    Review network configuration, firewall rules, and LightLLM server startup scripts to determine if WebSocket ports for the PD master node are listening on network interfaces accessible from untrusted sources.
    Affected if WebSocket endpoints for the PD master are exposed to network access beyond localhost or trusted internal networks.
  4. Inspect WebSocket endpoint authentication
    Examine the WebSocket handler code or configuration in the LightLLM PD master implementation to determine if authentication mechanisms are implemented on the binary frame endpoints.
    Affected if No authentication is required to send binary frames to the WebSocket endpoints.

The environment is affected if LightLLM version 1.1.0 or prior is running with PD disaggregation mode enabled and WebSocket endpoints are accessible without authentication.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Restrict network access to PD master WebSocket endpoints (e.g., firewall rules, network segmentation), implement strong authentication on these endpoints, and replace pickle.loads() with a safe deserialization method (e.g., JSON, MessagePack) or cryptographically signed payloads.

Recommended fix Moderate confidence

Latest stable release on github.com/ModelTC/lightllm (version higher than 1.1.0)

  1. 1. Identify all LightLLM deployments running version 1.1.0 or prior, specifically those with PD (prefill-decode) disaggregation mode enabled.
  2. 2. Check the official LightLLM GitHub repository (github.com/ModelTC/lightllm) for the latest release version that addresses this vulnerability.
  3. 3. Upgrade the LightLLM installation to the fixed release version that addresses the pickle.loads() deserialization issue.
  4. 4. After upgrading, verify that the PD master WebSocket endpoints now require authentication or use safe deserialization instead of pickle.
  5. 5. Restrict network access to PD master nodes to only trusted sources until the upgrade is complete as a temporary mitigation.
Caveat Review release notes for any breaking changes between 1.1.0 and the fixed version, particularly related to PD disaggregation mode configuration

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation4.0 h
  • Implementation16.0 h
  • Testing8.0 h
  • Review / QA4.0 h
32.0 hours of engineering $5,600
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $8,960.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-26220 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-26220 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data