PHP2Shell : See if you’re affected with a free external attack surface scan. Click Here > 

Back
New CVE Detected

CVE-2026-119706 – Unauthenticated RCE via Pickle Deserialization – InternLM LMDeploy 0.9.0 through 0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-119706 is an unauthenticated remote code execution vulnerability (CWE-502, Deserialization of Untrusted Data) in InternLM LMDeploy versions 0.9.0 through 0.18.0. The /update_weights endpoint deserializes attacker-supplied pickle data without validation. The CVE record rates it Critical (CVSS v4.0 base score 9.3).

Technical details

  • Root cause: The /update_weights HTTP endpoint unsafely deserializes pickle data using ForkingPickler.loads, with no validation of the input.
  • Trigger conditions: An attacker sends a request to /update_weights with a base64-encoded malicious pickle payload in the serialized_named_tensors parameter. No authentication is required.
  • Attack vector: Network, with no privileges and no user interaction required.
  • Impact: The attacker can run arbitrary OS commands as the api_server process, which can lead to full compromise of the LMDeploy inference host.

Affected software

  • InternLM LMDeploy 0.9.0 through 0.18.0 (inclusive)

Severity

  • CVSS v4.0 base score: 9.3 (Critical), with the vector AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H.
  • A CVSS v3.1 score could not be confirmed from the primary advisory sources reviewed, so none is stated here.

Mitigation and recommended actions

  • Immediate: Upgrade to a LMDeploy release that includes the fix from upstream pull request #4964. That change rejects pickle data on HTTP /update_weights requests by default. It accepts SafeTensors or structured tensor dictionaries instead. At the time of research, the PR page did not show a merge status or a release number, and the advisory does not name a fixed version. Confirm the fixed release with the LMDeploy maintainers before relying on a specific version.
  • Workarounds and network mitigations:
    • Do not expose the LMDeploy api_server to untrusted networks or the internet.
    • Restrict access to /update_weights with a firewall, reverse proxy or authentication layer.
    • After patching, do not set LMDEPLOY_ALLOW_PICKLE_UPDATE_PARAMS=1 unless the deployment is trusted. This opt-in re-enables pickle support.
  • Review exposed LMDeploy servers for unexpected requests to /update_weights and for signs of compromise.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge