CVE-2026-34753: vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
Noroxi assessment
Priority: Monitor (action score 21/100)
- Public proof-of-concept code exists (GitHub); there is no record of exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.25% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: vllm-project vllm 0.19.0.
Low priority for now. Upgrade to vllm-project vllm 0.19.0 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions. This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.
- Published
- Apr 6, 2026
- Updated
- Jun 17, 2026
- EPSS
- 0.2% · 17th percentile
- CWE
- CWE-918
Report tools
Action score
21
Monitor
Low priority for now.
- CVSS
- 21 / 40 · 5.4 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.2%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · GitHub_M
- 5.4
- NVD has not scored this yet; the score shown is the CNA’s.
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- Proof of concept exists, no weaponized module
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Running WordPress? Scan your site free with WP Lens
Noroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| vllm | vllm | cpe:2.3:a:vllm:vllm |
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- vllm vllm0.16.0 and later · before 0.19.0
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
vllm-project vllm
- >= 0.16.0, < 0.19.0affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | vllm | from 0.16.0 · before 0.19.0 | 0.19.0 |
Same product
vllm: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-22778vLLM leaks a heap address when PIL throws an error60This week
- CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration40Plan
- CVE-2024-11041Remote Code Execution in vllm-project/vllm40Plan
Published before and after this one in the same product
- ← EarlierCVE-2026-27893Mar 26, 2026 · vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out35Monitor
- ← EarlierCVE-2026-34760Apr 2, 2026 · vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models28Monitor
- Later →CVE-2026-34755Apr 6, 2026 · vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing26Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| vllm-project vllm | 0.19.0 · description | Vendor (CNA) |
| PyPI:vllm | 0.19.0 | Package registry (OSV) |
Exploit status
Proof of concept available
A public proof of concept or detection signature exists. Exploit knowledge is out there; don't delay patching.
Evidence
- Proof-of-concept repository on GitHub ×1
Noroxi does not host or link to exploit code. Metasploit module names and Nuclei template ids are shown (names, not code); Exploit-DB entries and PoC repositories are given as counts only.
| Source | Kind | Date |
|---|---|---|
| Proof-of-concept repository on GitHub | stars:0 | 2026-05-03 |
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
- Published
- First PoC+26 d
- TodayNov 6, 2026+214 d
No history yet (it accumulates with the daily EPSS job).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
No commit or PR link among the references.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
No credits in the CNA record.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-2596028 days apartSSRF Protection Bypass in vLLM39Monitor
- CVE-2026-116176202 days apartvLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector35Monitor
- CVE-2026-2477969 days apartvLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`28Monitor
- CVE-2026-73560133 days apartvLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections26Monitor
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
- CVE-2026-4874677 days apartvLLM: OpenAI auth bypass36Monitor
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- low · data can be read
- Integrity
- none
- Availability
- low · the service can be disrupted
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality impact
- Low
- Integrity impact
- None
- Availability impact
- Low
Weakness class (CWE)
CWE-918 · Server-Side Request Forgery (SSRF)CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
nvd-secondary
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
ATT&CK techniques
—
Change log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Vendor advisories and official records. Exploit/PoC links are deliberately left out.