Read the docs
TI-2026-80504 Aliases CVE-2026-115912GHSA-6757-hggm-hp2w

Unsafe pickle deserialization in vLLM multimodal shared memory

Priority MEDIUM 41CWE-502Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Code execution
Confidentiality · integrity · availability
High · High · High
Fix status
Partial Red Hat: 3 without a fix

Attack profile from CVSS 3.1 · NVD. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-502.

Summary

vLLM before 0.32.0 is affected. A flaw in deserialization of untrusted data (CWE-502) lets workers trust forged shared-memory address and monotonic_id values in public multimodal features, then pass attacker-selected bytes to pickle.loads(). An authenticated remote attacker with low privileges can execute arbitrary Python code in scale-out deployments with shared-memory multimodal caching enabled, even when insecure serialization is disabled.

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

Description from the CNA

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.0051 43rd percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.32.0vllm (PyPI): 0.32.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllmbefore 0.32.00.32.0Patch availableCNA
—vllm (PyPI)before 0.32.00.32.0Patch availableGHSA-6757-hggm-hp2w
  • vllm Vendorvllm-project Affected before 0.32.0 Fixed in 0.32.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected before 0.32.0 Fixed in 0.32.0 Patch available GHSA-6757-hggm-hp2w

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*before 0.32.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions before 0.32.0 Vulnerable ·vLLM

Remediation

Upgrade the vllm package on PyPI to version 0.32.0. Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI) are listed as affected, and the sources list no fixed version for them.

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

  • Fix · CNA vllm (vllm-project) Fixed in 0.32.0
  • Fix · GHSA-6757-hggm-hp2w vllm (PyPI) Fixed in 0.32.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet
Not affected: 1 product
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-26 Threatist record created from CVE-2026-115912
  2. 2026-10-26 CISA SSVC decision points changed
  3. 2026-10-26 Priority changed: MEDIUM → LOW
  4. 2026-10-27 Affected versions changed · Red Hat
  5. 2026-10-27 CVSS score added · Red Hat
  6. 2026-10-28 CVSS score added · NVD
  7. 2026-10-28 Priority changed: LOW → MEDIUM
  8. 2026-10-28 Alias added: GHSA-6757-hggm-hp2w
  9. 2026-10-28 Fix available: PyPI/[email protected] · GHSA-6757-hggm-hp2w
  10. 2026-10-28 CVSS score added · GHSA-6757-hggm-hp2w
  11. 2026-10-28 Weakness changed · GHSA-6757-hggm-hp2w
  12. 2026-10-28 6 new references · GHSA-6757-hggm-hp2w
  13. 2026-10-30 Affected versions changed · Red Hat

References

Patch 3

Advisory 1

Other 2

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences