PYSEC-2026-3996 CVE-2026-93436
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments.
- Severity
- 0.0 / 10
- High · CVSS 4.0
- Exploit chance (EPSS)
- 0.76%
- Chance of exploitation in the next 30 days. Higher than 55.15% of scored vulnerabilities.
- Known exploited
- No
- Not in CISA's catalog
- Weakness
- CWE-401 Missing Release of Memory after Effective Lifetime
- Fix
0.30.0- Upgrade vllm to this version or later
Description
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
Affected versions
PyPI
| Package | Vulnerable | Fixed in |
|---|---|---|
| vllm | < 0.30.0 |
0.30.0 |
How to fix
Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.
vllm PyPI → 0.30.0
- pip
pip install --upgrade "vllm>=0.30.0"- poetry
poetry add "vllm>=0.30.0"- uv
uv add "vllm>=0.30.0"
Severity breakdown
CVSS 4.0 0.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/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
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- None
- Privileges required
- None
- User interaction
- None
- Confidentiality (vulnerable system)
- None
- Integrity (vulnerable system)
- None
- Availability (vulnerable system)
- High
- Confidentiality (subsequent systems)
- None
- Integrity (subsequent systems)
- None
- Availability (subsequent systems)
- None
- Exploit maturity
- Not defined
- Scope
- X
CVSS 3.1 7.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- None
- Integrity
- None
- Availability
- High
Weakness
CWE-401: Missing Release of Memory after Effective Lifetime
The product does not sufficiently track and release allocated memory after it has been used, making the memory unavailable for reallocation and reuse.
How to prevent it
- Implementation: Choose a language or tool that provides automatic memory management, or makes manual memory management less error-prone. For example, glibc in Linux provides protection against free of invalid pointers. When using Xcode to target OS X or iOS, enable automatic reference counting (ARC) [REF-391]. To help correctly and consistently manage memory when programming in C++, consider using a smart pointer class such as std::auto_ptr (defined by ISO/IEC ISO/IEC 14882:2003), std::shared_ptr and std::unique_ptr (specified by an upcoming revision of the C++ standard, informally referred to as C++ 1x), or equivalent solutions such as Boost.
- Architecture and Design: Use an abstraction library to abstract away risky APIs. Not a complete solution.
- Architecture and Design, Build and Compilation: Consider using the Boehm-Demers-Weiser garbage collector (bdwgc), which can help avoid leaks.
References
Advisories
Fixes and patches
Packages
Other links
Timeline
- Published
- Last updated by the source
- Latest EPSS score
Related advisories
| Advisory | Severity | Why it's related |
|---|---|---|
| GHSA-8397-8qf6-f2gm vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine | Medium | Also affects vllm |
| GHSA-x567-49g5-p4cf vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs | Medium | Also affects vllm |
| GHSA-vvpg-rrww-wpmh vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server | Medium | Also affects vllm |
| GHSA-q97c-p368-75c4 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) | Medium | Also affects vllm |
| GHSA-h3rc-j82p-2c3h vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE | High | Also affects vllm |
| GHSA-gq5q-89c7-vhvx vLLM DeepSeek-OCR image processing vulnerable to denial of service | Medium | Also affects vllm |
| GHSA-6757-hggm-hp2w vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled | High | Also affects vllm |
| GHSA-542m-9234-8gvf vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool | Medium | Also affects vllm |
MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.
Check your repos with MergeHarbor