Medium

CVE-2026-12491 — Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.

Published Jun 17, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: redhat

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.2% (30-day exploitation probability)+2
Technical severity (medium)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.24%

ahead of 14% of scored CVEs · Oct 14, 2026

Affects

Red Hat

Ai Inference Server and 3 more

CVSS base

4.8

Medium · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

None

none · proof-of-concept · active

Automatable

can an attacker script the kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (Red Hat Ai Inference Server, Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat Red Hat OpenShift AI (RHOAI)…).
The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
No fix documented in the sources: reduce exposure and monitor the vendor advisory.
Search available logs for exploit probes, errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
Red Hat	Ai Inference Server	versions not specified by the source	Vulnerable	CVE Program (cve.org) e CISA ADP
Red Hat	Red Hat Enterprise Linux AI (RHEL AI) 3	versions not specified by the source	Vulnerable	CVE Program (cve.org) e CISA ADP
Red Hat	Red Hat OpenShift AI (RHOAI)	versions not specified by the source	Vulnerable	CVE Program (cve.org) e CISA ADP
Vllm-project	Vllm-project/vllm	≥ 0.11.0 and < 0.24.0	Vulnerable	CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

High

Privileges required

None

User interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

Low

Availability

Low

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
4.8	CVSS 3.1	Medium	2.2	2.5	secalert@redhat.com via NIST National Vulnerability Database
4.8	CVSS 3.1	Medium	—	—	redhat via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L (score shown at the top: secalert@redhat.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-115

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.24%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).

web/proxy/WAF logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first.

2026
Affected products added · vllm-project/vllm, red hat/red hat ai inference server, red hat/red hat enterprise linux ai (rhel ai) 3, red hat/red hat
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 13, 2026
CVSS changed · 4.8
Oct 13, 2026 · NIST National Vulnerability Database
Source status changed · → Awaiting Analysis
Oct 13, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 13, 2026 · NIST National Vulnerability Database
CVE published
Jun 17, 2026 · redhat

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

2 on the record

bugzilla.redhat.com/show_bug.cgi
issue-tracking, x_refsource_REDHAT, NIST National Vulnerability Database
access.redhat.com/security/cve/CVE-2026-12491
vdb-entry, x_refsource_REDHAT, NIST National Vulnerability Database

Elsewhere on this site

Red Hat
every CVE for this vendor

CWE-115
other pages naming this weakness

Related CVEs (same products)

Medium CVE-2026-109311 vLLM before 0.29.0 Heap Overflow DoS via IAMF Audio Transcription Upload 3d
Medium CVE-2026-105922 vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service 9d
Medium CVE-2026-105775 vllm-project vLLM Completions Request mamba_mixer2.py conv_ssm_forward out-of-bounds 9d
Medium CVE-2026-105759 vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service) 9d
Medium CVE-2026-105755 vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank` 9d
Medium CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion 9d

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No fixed version, patch or mitigation documented.
No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-12491 is "Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations", rated Medium. It affects Ai Inference Server (Red Hat); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 4.8 describes technical severity. EPSS 0.24% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.