Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vLLM package (versions >=0.6.4, <0.9.0) is vulnerable to a regular expression denial of service in its pythonic tool parser, where a nested regex can take exponential time on crafted input. An attacker who can send requests that reach this parser can exhaust CPU and tie up resources, making the service unavailable. Upgrade to vLLM 0.9.0 or later. The source notes the regex may still be slow on long input after the fix.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.5 | Medium | 3.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0054, the 46th percentile, on 17 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:40 UTC First seen by agentprime
- 31 Oct 2026, 14:40 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-w6q7-j642-7c25
- OSV: GHSA-w6q7-j642-7c25
- github.com/vllm-project/vllm/security/advisories/GHSA-w6q7-j642-7c25
- nvd.nist.gov/vuln/detail/CVE-2025-48887
- github.com/vllm-project/vllm/pull/18454
- github.com/vllm-project/vllm/commit/4fc1bf813ad80172c1db31264beaef7d93fe0601
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-50.yaml
- github.com/vllm-project/vllm