CVE-2026-115912: vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Noroxi assessment
Priority: Monitor (action score 35/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.51% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: vllm-project vllm 0.32.0.
Low priority for now. Upgrade to vllm-project vllm 0.32.0 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
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.
- Published
- Oct 26, 2026
- Updated
- Oct 28, 2026
- EPSS
- 0.5% · 44th percentile
- CWE
- CWE-502
Report tools
Action score
35
Low priority for now.
- CVSS
- 35 / 40 · 8.8 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.5%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- total
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- 8.8
- CNA · GitHub_M
- 7.5
- 1.3 point gap
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Is your version affected? Check itNoroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| vllm | vllm | cpe:2.3:a:vllm:vllm |
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
vllm-project vllm
- < 0.32.0affected
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- vllm vllmbefore 0.32.0
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | vllm | before 0.32.0 | 0.32.0 |
Same product
vllm: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-22778vLLM leaks a heap address when PIL throws an error60This week
- CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration40Plan
- CVE-2024-11041Remote Code Execution in vllm-project/vllm40Plan
Published before and after this one in the same product
- ← EarlierCVE-2026-116181Oct 25, 2026 · vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids28Monitor
- ← EarlierCVE-2026-115911Oct 26, 2026 · vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool26Monitor
- Later →CVE-2026-115913Oct 26, 2026 · vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM…26Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| vllm-project vllm | 0.32.0 · description | Vendor (CNA) |
| PyPI:vllm | 0.32.0 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
- Published
- Fix recordedsame day
- TodayNov 13, 2026+18 d
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2025-47277524 days apartvLLM Allows Remote Code Execution via PyNcclPipe Communication Service39Monitor
- CVE-2025-30165538 days apartRemote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration32Monitor
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
- CVE-2026-48746126 days apartvLLM: OpenAI auth bypass36Monitor
Not on record for this CVE: researcher credit · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- high · data can be read
- Integrity
- high · data or configuration can be modified
- Availability
- high · the service can be disrupted
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality impact
- High
- Integrity impact
- High
- Availability impact
- High
Weakness class (CWE)
CWE-502 · Deserialization of Untrusted DataCVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
nvd-primary
Root cause
Data received over the network is deserialized into the language’s native object format without verifying its source. Code paths inside the object can be triggered during deserialization.
The bug in code
The whole CWE-502 classA representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.
Vulnerable
payload = sock.recv(65536)
job = pickle.loads(payload)Fixed
payload = sock.recv(65536)
if not hmac.compare_digest(sign(payload), header_sig):
raise PermissionError("invalid signature")
job = JobSchema.validate(json.loads(payload))Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
ATT&CK techniques
—
Change log
- CVSS7.5 → 8.8
- SSVC exploitation— → none
- Exploit maturity— → none
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (3 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.