Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Vulnerable versions of the vllm package are >=0.6.4 and <0.12.0, fixed in 0.12.0. An attacker who can send requests to a server running an Idefics3-based multimodal model can crash the engine with a specially crafted 1x1 pixel image, causing a denial of service that terminates the server. Upgrade vllm to 0.12.0 or later. The source gives no workaround beyond validating image input.
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 0.0044, the 38th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:34 UTC First seen by agentprime
- 31 Oct 2026, 14:34 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-grg2-63fw-f2qr
- OSV: GHSA-grg2-63fw-f2qr
- github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr
- nvd.nist.gov/vuln/detail/CVE-2026-22773
- github.com/vllm-project/vllm/pull/29881
- github.com/vllm-project/vllm/commit/0ec84221718d920c3f46da879cc354f94b8fb59e
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-143.yaml
- github.com/vllm-project/vllm