Vulnerability in vllm (CVE-2026-73559)
Summary
Vulnerability in vllm (CVE-2026-73559). Risk of unauthorized operations or information disclosure. Exploitable via prompt. Mitigation: upgrade to 0.19.0 or later.
Original description
The description as published by the source.
Summary
The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a response slot per prompt. An authenticated API client can therefore turn one request into an attacker-chosen number of backend subrequests before any aggregate request-count budget is enforced.
Technical Details
CompletionRequest.prompt allows both list-shaped prompt inputs and scalar prompts:
# vllm/entrypoints/openai/completion/protocol.py
prompt: (
list[Annotated[int, Field(ge=0)]]
| list[list[Annotated[int, Field(ge=0)]]]
| str
| list[str]
| None
) = None
The validator only requires some prompt-like input to be present:
def validate_prompt_and_prompt_embeds(cls, data):
prompt = data.get("prompt")
prompt_embeds = data.get("prompt_embeds")
...
if prompt_is_empty and embeds_is_empty:
raise VLLMValidationError(...)
The renderer then expands list-shaped prompts as a sequence. prompt_to_seq() wraps a scalar string or a single token-id list, but returns a list[str] or list[list[int]] unchanged:
# vllm/renderers/inputs/preprocess.py
def prompt_to_seq(prompt_or_prompts):
if isinstance(prompt_or_prompts, (dict, str, bytes)) or (
len(prompt_or_prompts) > 0 and is_list_of(p…
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-73559 has been found in vllm.
Attackers can target a specific entry point like prompt over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: upgrade vllm to 0.19.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-73559" on the vendor's site.
CVE-2026-73559 (vllm) — CWE-400 / CVSS v3 6.5
Attack vector: remote (network-reachable) / no user interaction
Attack surface: prompt / CompletionRequest.prompt / vllm / main
Patched: 0.19.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-400) exists in vllm. Attackers reach the vulnerable code path via prompt.
Check the vendor advisory for the affected versions of vllm. Attack surface: prompt / CompletionRequest.prompt / vllm / main.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to 0.19.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'vllm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
vllmを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade vllm to 0.19.0ステージング環境で 0.19.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory nvd.nist.gov
- advisory github.com
- package github.com
- package pypi.org
- web github.com
- web github.com
- web github.com
- web github.com