# CVE-2026-73556: vLLM ReDoS in lm-format-enforcer backend regex parsing

Source: https://junglewise.ai/threats/cve-2026-73556-vllm-redos-in-lm-format-enforcer-backend-regex-parsing  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-13. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-73556 · Severity: medium · CVSS 5.3 · Published 2026-08-13

vLLM is an open-source large language model inference engine. The lm-format-enforcer backend, used to constrain generated output to match user-supplied regex patterns, fails to validate or time-limit regex compilation. An attacker can submit a catastrophic regex (such as `(a{1,300}){300}`) that causes the regex compiler to hang indefinitely, consuming a CPU core and blocking all concurrent structured-output requests on that worker.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-73556 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-73556 being exploited in the wild.

**How severe is CVE-2026-73556?** Medium severity, with a CVSS score of 5.3, published 13 August 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.26.0.

**Is there a fix for CVE-2026-73556?** Yes. vllm (PyPI): upgrade to 0.26.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-73556 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-73556?** Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.26.0 or later

  ```sh
  pip install "vllm>=0.26.0"
  ```


## Technical details

The vulnerability is a Regular Expression Denial of Service (ReDoS) in vLLM's lm-format-enforcer structured-output backend (vllm/v1/structured_output/backend_lm_format_enforcer.py, line 110). The backend calls `lmformatenforcer.RegexParser(grammar_spec)` directly on user-supplied regex strings without timeout or buildability checks. The underlying interegular FSM construction exhibits catastrophic complexity on exponential patterns like `(a{1,300}){300}`, which does not complete in 20+ seconds and pegs a CPU core at 100%. The sibling xgrammar and outlines backends were patched for the same issue (GHSA-rwxx-mrjm-wc2m) by wrapping regex compile in `compile_regex_with_timeout`, but lm-format-enforcer was overlooked. The attack is unauthenticated (vLLM has no auth by default) and requires only network access and selection of the lm-format-enforcer backend via `--structured-outputs-config` (not the default). Patched in version 0.26.0.

## Affected products

- vLLM Project vLLM < 0.26.0

## Identifiers

- CVE-2026-73556
- GHSA-48jh-3gj7-fg8v
- PYSEC-2026-3933

## Timeline

- 2026-09-04: disclosed: GitHub Security Advisory published
- 2026-09-04: patched: Fix released in v0.26.0

## References

- [https://api.github.com/users/CyberKareem](https://api.github.com/users/CyberKareem)
- [https://github.com/CyberKareem](https://github.com/CyberKareem)
- [https://api.github.com/users/CyberKareem/gists%7B/gist_id%7D](https://api.github.com/users/CyberKareem/gists%7B/gist_id%7D)
- [https://api.github.com/users/CyberKareem/repos](https://api.github.com/users/CyberKareem/repos)
- [https://avatars.githubusercontent.com/u/67718280?v=4](https://avatars.githubusercontent.com/u/67718280?v=4)
- [https://api.github.com/users/CyberKareem/events%7B/privacy%7D](https://api.github.com/users/CyberKareem/events%7B/privacy%7D)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)