Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM from 0.11.0 before 0.24.0 does not normalize EXIF orientation or flatten PNG transparency (tRNS) before converting images to RGB. An attacker who can submit images can make the model see altered content, such as wrongly oriented images or hidden overlays becoming visible. Upgrade to vLLM 0.24.0.
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 |
|---|---|---|---|---|
| 4.8 | Medium | 3.1 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L | CNA (redhat) |
- CISA KEV Not listed.
- EPSS 0.0024, the 15th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:11 UTC First seen by agentprime
- 31 Oct 2026, 14:11 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-8jr5-v98p-w75m
- OSV: GHSA-8jr5-v98p-w75m
- github.com/vllm-project/vllm/security/advisories/GHSA-8jr5-v98p-w75m
- nvd.nist.gov/vuln/detail/CVE-2026-12491
- github.com/vllm-project/vllm/pull/44974
- github.com/vllm-project/vllm/commit/cf1c90672404548aa3bc51f92c4745576a65ee26
- access.redhat.com/security/cve/CVE-2026-12491
- bugzilla.redhat.com/show_bug.cgi?id=2489786
- github.com/advisories/GHSA-8jr5-v98p-w75m
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3406.yaml
- github.com/vllm-project/vllm
- pypi.org/project/vllm