CVE Intelligence
High SSRF

CVE-2025-6242 — Vllm: server side request forgery (ssrf) in mediaconnector

A Server-Side Request Forgery (SSRF) vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The load_from_url and load_from_url_async methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources.

Published Oct 7, 2025 · Updated Oct 18, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: redhat

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 (high)+6

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
0.25%
ahead of 15% of scored CVEs · Oct 19, 2026
Affects
Red Hat
Ai Inference Server and 2 more
CVSS base
7.1
High · 3 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
No
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.

  • Pip Vllm: fixed in version 0.11.0 — github.com (GitHub Security Advisories)

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.

  1. Identify exposed assets running the affected vendor/product/version combinations (Red Hat Ai Inference Server, Red Hat Red Hat Enterprise Linux AI (RHEL AI), Pip Vllm).
  2. Apply the fixed version or the patch documented under Remediation.
  3. Search available logs for exploit probes matching the vulnerability class (ssrf), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
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) versions not specified by the source Vulnerable CVE Program (cve.org) e CISA ADP
Pip Vllm ≥ 0.5.0 and < 0.11.0 Vulnerable GitHub Security Advisories

Attack characteristics

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

Attack vector
Network
Attack complexity
High
Privileges required
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
Low
Availability
High

Every base score collected

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

ScoreVersionSeverityExpl.ImpactScored by
7.1 CVSS 3.1 High 1.6 5.5 secalert@redhat.com via NIST National Vulnerability Database
7.1 CVSS 3.1 High — — GitHub, Inc. via GitHub Security Advisories
7.1 CVSS 3.1 High — — redhat via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:H (score shown at the top: secalert@redhat.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-918 · Server-Side Request Forgery (SSRF)

Other CVEs with this weakness →

EPSS over time FIRST

Oct 18, 2026 → Oct 19, 2026 · 2 reading(s) · max 0.25%

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).
  • Monitor outbound requests from the server to internal IPs and cloud metadata endpoints.
web/proxy/WAF logsnetwork IDS/IPSegress traffic

Timeline

What happened to this CVE, newest first.

  • 2026
  • Fix documented
    Oct 18, 2026 · GitHub Security Advisories
  • Affected products added · pip/vllm
    Oct 18, 2026 · GitHub Security Advisories
  • Affected products added · red hat/red hat ai inference server, red hat/red hat enterprise linux ai (rhel ai)
    Oct 18, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 18, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 18, 2026
  • CVSS changed · 7.1
    Oct 18, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 18, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 18, 2026 · Alertas do Telegram
  • 2025
  • CVE published
    Oct 7, 2025 · redhat

Source activity

Repeated readings are counted rather than listed.

  • 2× References added · Oct 18, 2026 – Oct 18, 2026
  • 1× Official description updated · Oct 18, 2026 – Oct 18, 2026

References

6 on the record

Elsewhere on this site

Red Hat
every CVE for this vendor
SSRF
same class
CWE-918
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion 14d
  • CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts Aug 13, 2026
  • CVE-2026-56210 Libaom: libaom: heap-buffer-overflow read via missing bounds check in ctrl_set_layer_id Jun 19, 2026
  • CVE-2026-56209 Libaom: libaom: arbitrary address write via svc layer context oob and cyclic refresh map pointer hijack Jun 19, 2026
  • CVE-2026-56208 Libaom: libaom: heap buffer overflow in av1 encoder first-pass stats buffer via lap mode Jun 19, 2026
  • CVE-2026-56211 Libaom: libaom: remote code execution via svc layer context handling with attacker-controlled frames Jun 19, 2026

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 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-2025-6242 is "Vllm: server side request forgery (ssrf) in mediaconnector", rated High. 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 7.1 describes technical severity. EPSS 0.25% 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.

Sign in or create an account to comment and suggest corrections.