Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
MEDIUM severity

CVE-2026-73556 — vllm

MEDIUMFix: vllm-project/vllm@c9a788e

CVE-2026-73556 is a medium-severity (CVSS 5.3) Uncontrolled Resource Consumption vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of CVE-2026-55574

Also known asGHSA-48jh-3gj7-fg8vPYSEC-2026-3933
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Oct 18, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Proof-of-concept exploit code exists

  • CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-73556.

EPSS Exploitation Probability

via FIRST.org ↗
0.5%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs43th percentile — riskier than 43% of all scored CVEsHighest risk
0.00%0.34%0.68%1.01%0.3%0.5%0.5%Sep 26Oct 26Oct 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

CVE-2026-73556 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 391,411 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Summary

The fix for GHSA-rwxx-mrjm-wc2m ("ReDoS via structured_outputs.regex compiled without timeout") wrapped the regex compile in the xgrammar and outlines backends with compile_regex_with_timeout (and, for outlines, validate_regex_is_buildable). The lm-format-enforcer backend was left unguarded: it compiles the attacker-supplied regex with no timeout and no buildability check. A single request with a catastrophic regex hangs the structured-output compile step and stalls the engine worker (denial of service).

Affected code (HEAD d6d39c1)

vllm/v1/structured_output/backend_lm_format_enforcer.py:

  • line 110: character_level_parser = lmformatenforcer.RegexParser(grammar_spec) — builds an interegular FSM from the attacker regex synchronously, no timeout.
  • line 155: validate_structured_output_request_lm_format_enforcer returns immediately on if so_params.regex: — no validation.

Sibling backends that WERE patched by GHSA-rwxx:

  • backend_xgrammar.py:92 → compile_regex_with_timeout(...).
  • backend_outlines.py:65 → compile_regex_with_timeout(...) (plus validate_regex_is_buildable).

lm-format-enforcer uses the same interegular DFA-construction primitive the advisory cites for the outlines backend.

Reproduction (runtime-verified against the sink)

The sink lmformatenforcer.RegexParser(<regex>) was exercised directly (this is exactly what the backend calls):

baseline  '[0-9]{3}'          -> 0.0002 s
attacker  '(a{1,300}){300}'   -> DID NOT COMPLETE in 20 s (one core pegged at 100% in interegular FSM construction)

End-to-end: start vllm serve <model> --structured-outputs-config '{"backend":"lm-format-enforcer"}', then POST /v1/completions with {"structured_outputs":{"regex":"(a{1,300}){300}"}, ...}. The request never returns; because grammar compile runs in the engine's structured-output path, concurrent requests stall = worker-level DoS. The identical request against the outlines backend is bounded by compile_regex_with_timeout and returns a clean error.

Impact

Unauthenticated denial of service (vLLM ships with no authentication by default). One request pegs a CPU core and blocks the structured-output engine path.

Reachability precondition: the operator must have selected backend=lm-format-enforcer via --structured-outputs-config (the default is auto → xgrammar). This is the same opt-in tier as the outlines backend that GHSA-rwxx already covered.

Suggested remediation

Route the lm-format-enforcer regex compile (backend_lm_format_enforcer.py:110) through the same compile_regex_with_timeout guard already applied to the xgrammar and outlines backends, and reject un-buildable / oversized patterns in validate_structured_output_request_lm_format_enforcer.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllmall versions0.26.0pip install --upgrade 'vllm==0.26.0'

Affected Products

1 product · 1 configurations
Application
vllmvllm
< 0.26.0
range

Detection & mitigation playbook

Open-source dependency

  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.26.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-73556 is resolved across your whole dependency graph.

  3. Workarounds

    Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatImportant

This flaw in vLLM is rated as Important because an unauthenticated remote attacker can trigger a Regular Expression Denial of Service (ReDoS). By sending a specially crafted regular expression to the `/v1/completions` endpoint, the attacker can cause the vLLM service to consume excessive CPU resources, leading to a…

ProductFixed inAdvisory
Red Hat AI Inference Server 3.3rhaiis/vllm-cuda-rhel9:1789582776RHSA-2026:68699
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1789681201RHSA-2026:69464
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1789681128RHSA-2026:69466
Red Hat AI Inference Server 3.4rhaii/vllm-cuda-rhel9:1789681126RHSA-2026:69467
Red Hat AI Inference Server 3.4rhaii/vllm-rocm-rhel9:1789681126RHSA-2026:69469
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1790075793RHSA-2026:70965
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1790076141RHSA-2026:70969
Red Hat AI Inference Server 3.4rhaii/vllm-cuda-rhel9:1790090131RHSA-2026:70979

Frequently Asked Questions

### Summary The fix for `GHSA-rwxx-mrjm-wc2m` ("ReDoS via `structured_outputs.regex` compiled without timeout") wrapped the regex compile in the **xgrammar** and **outlines** backends with `compile_regex_with_timeout` (and, for outlines, `validate_regex_is_buildable`). The **lm-format-enforcer** backend was left unguarded: it compiles the attacker-supplied regex with no timeout and no buildability check. A single request with a catastrophic regex hangs the structured-output compile step and stalls the engine worker (denial of service). ### Affected code (HEAD d6d39c1) `vllm/v1/structured_ou
O3 Security · Impact-Aware SCA

Is CVE-2026-73556 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works
CVE-2026-73556: vllm DoS — Fixed in 0.26.0