CVE-2026-34755: vLLM Denial of Service Vulnerability

Q: What is CVE-2026-34755?

CVE-2026-34755 is a security vulnerability in vLLM involving Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing under CWE-770: Allocation of Resources Without Limits or Throttling.

Q: Which vLLM versions are affected?

Affected versions include releases prior to 0.19.0 across affected packages: vllm.

Q: What version fixes CVE-2026-34755?

Upgrading to 0.19.0 (or the latest patched release for your respective branch) resolves the vulnerability.

Q: Is vllm affected?

Yes, vllm is affected in releases prior to 0.19.0. Upgrade your dependency to 0.19.0 or later.

Q: What is the CVSS score of CVE-2026-34755?

CVE-2026-34755 has a CVSS v3.1 base score of 6.5 (MODERATE) with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.

Q: What CWE is associated with CVE-2026-34755?

CVE-2026-34755 is classified under CWE-770: Allocation of Resources Without Limits or Throttling (The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.).

Q: How can I check PyPI dependencies for CVE-2026-34755?

Run the dependency tree command: 'pip show vllm'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.

MODERATE

Advisory Identifier: GHSA-pq5c-rjhq-qp7p

CVSS 6.5

CWE-770

Published 2026-04-03

Advisory Summary

CVE-2026-34755 is a MODERATE (CVSS 6.5) denial of service vulnerability (CWE-770: Allocation of Resources Without Limits or Throttling) affecting vLLM libraries in the PyPI ecosystem. The issue involves denial of service via unbounded frame count in video/jpeg base64 processing. Remediation is available by upgrading affected packages to version 0.19.0.

CVE-2026-34755 at a Glance

CVE Identifier CVE-2026-34755

GHSA Identifier GHSA-pq5c-rjhq-qp7p

Severity MODERATE

CVSS v3.1 Base Score 6.5

CWE Classification CWE-770: Allocation of Resources Without Limits or Throttling

Affected Product vLLM

Package Ecosystem PyPI

Published Date 2026-04-03

Last Updated 2026-08-25

Security Impact

CVSS: 6.5

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H).

Attack Vector Network (AV:N)

Attack Complexity Low (AC:L)

Privileges Required Low (PR:L)

User Interaction None (UI:N)

Scope Unchanged (S:U)

Confidentiality None (C:N)

Integrity None (I:N)

Availability High (A:H)

How to Fix CVE-2026-34755

To remediate this vulnerability, upgrade all affected vLLM dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

vllm fixed: 0.19.0

pip install vllm>=0.19.0

Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show vllm

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-34755, inspect your installed packages using pip:

pip show vllm

Analyze the terminal output to locate any version of vLLM in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.19.0), your application is affected.

Note: The pip show vllm command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-770: Allocation of Resources Without Limits or Throttling, where the product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated. In vLLM, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

## Summary The `VideoMediaIO.load_base64()` method at `vllm/multimodal/media/video.py:51-62` splits `video/jpeg` data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The `num_frames` parameter (default: 32), which is enforced by the `load_bytes()` code path at line 47-48, is completely bypassed in the `video/jpeg` base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. ## Details ### Vulnerable code ```python # video.py:51-62 def load_base64(self, media_type: str, data: str) -> tuple[npt.NDArray, dict[str, Any]]: if media_type.lower() == "video/jpeg": load_frame = partial(self.image_io.load_base64, "image/jpeg") return np.stack( [np.asarray(load_frame(frame_data)) for frame_data in data.split(",")] # ^^^^^^^^^^ # Unbounded split — no frame count limit ), {} return self.load_bytes(base64.b64decode(data)) ``` The `load_bytes()` path (line 47-48) properly delegates to a video loader that respects `self.num_frames` (default 32). The `load_base64("video/jpeg", ...)` path bypasses this limit entirely — `data.split(",")` produces an unbounded list and every frame is decoded into a numpy array. ### video/jpeg is part of vLLM's public API `video/jpeg` is a vLLM-specific MIME type, not IANA-registered. However it is part of the public API surface: - `encode_video_url()` at `vllm/multimodal/utils.py:96-108` generates `data:video/jpeg;base64,...` URLs - Official test suites at `tests/entrypoints/openai/test_video.py:62` and `tests/entrypoints/test_chat_utils.py:153` both use this format ### Memory amplification Each JPEG frame decodes to a full numpy array. For 640x480 RGB images, each frame is ~921 KB decoded. 5000 frames = ~4.6 GB. `np.stack()` then creates an additional copy. The compressed JPEG payload is small (~100 KB for 5000 frames) but decompresses to gigabytes. ### Data flow ``` POST /v1/chat/completions → chat_utils.py:1434 video_url type → mm_parser.parse_video() → chat_utils.py:872 parse_video() → self._connector.fetch_video() → connector.py:295 fetch_video() → load_from_url(url, self.video_io) → connector.py:91 _load_data_url(): url_spec.path.split(",", 1) → media_type = "video/jpeg" → data = "<frame1>,<frame2>,...,<frame10000>" → connector.py:100 media_io.load_base64("video/jpeg", data) → video.py:54 data.split(",") ← UNBOUNDED → video.py:55-57 all frames decoded into numpy arrays → video.py:56 np.stack([...]) ← massive combined array → OOM ``` `connector.py:91` uses `split(",", 1)` which splits on only the first comma. All remaining commas stay in `data` and are later split by `video.py:54`. ### Comparison with existing protections | Code Path | Frame Limit | File | |-----------|-------------|------| | `load_bytes()` (binary video) | Yes — `num_frames` (default 32) | video.py:46-49 | | `load_base64("video/jpeg", ...)` | No — unlimited `data.split(",")` | video.py:51-62 |

CVE-2026-34755 Affected vLLM Versions

1 component(s)

Fixed Versions:

0.19.0

Product / Package	Ecosystem	Affected Versions	Fixed Version
vllm pypi/vllm	PyPI	≥ 0.7.0 < 0.19.0	0.19.0

References

GitHub Advisory / Wiki ADVISORY

https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p

NVD — CVE-2026-34755 NVD

https://nvd.nist.gov/vuln/detail/CVE-2026-34755

vLLM Source Repository REPOSITORY

https://github.com/vllm-project/vllm/pull/38636

Security Fix Commit FIX COMMIT

https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395

vLLM Security Information SECURITY

https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json

vLLM Source Repository REPOSITORY

https://github.com/vllm-project/vllm

vLLM Source Repository REPOSITORY

https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-144.yaml

bugzilla.redhat.com/show_bug.cgi WEB

https://bugzilla.redhat.com/show_bug.cgi?id=2455403

vLLM Security Information SECURITY

https://access.redhat.com/security/cve/CVE-2026-34755

access.redhat.com/errata/rhsa-2026:59... WEB

https://access.redhat.com/errata/RHSA-2026:59151

access.redhat.com/errata/rhsa-2026:59... WEB

https://access.redhat.com/errata/RHSA-2026:59144

access.redhat.com/errata/rhsa-2026:57... WEB

https://access.redhat.com/errata/RHSA-2026:57390

access.redhat.com/errata/rhsa-2026:57... WEB

https://access.redhat.com/errata/RHSA-2026:57389

access.redhat.com/errata/rhsa-2026:57... WEB

https://access.redhat.com/errata/RHSA-2026:57387

access.redhat.com/errata/rhsa-2026:57... WEB

https://access.redhat.com/errata/RHSA-2026:57380

access.redhat.com/errata/rhsa-2026:36... WEB

https://access.redhat.com/errata/RHSA-2026:36006

access.redhat.com/errata/rhsa-2026:36... WEB

https://access.redhat.com/errata/RHSA-2026:36005

Frequently Asked Questions

What is CVE-2026-34755?

CVE-2026-34755 is a security vulnerability in vLLM involving Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing under CWE-770: Allocation of Resources Without Limits or Throttling.

Which vLLM versions are affected?

Affected versions include releases prior to 0.19.0 across affected packages: vllm.

What version fixes CVE-2026-34755?

Upgrading to 0.19.0 (or the latest patched release for your respective branch) resolves the vulnerability.

Is vllm affected?

Yes, vllm is affected in releases prior to 0.19.0. Upgrade your dependency to 0.19.0 or later.

What is the CVSS score of CVE-2026-34755?

CVE-2026-34755 has a CVSS v3.1 base score of 6.5 (MODERATE) with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.

What CWE is associated with CVE-2026-34755?

CVE-2026-34755 is classified under CWE-770: Allocation of Resources Without Limits or Throttling (The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.).

How can I check PyPI dependencies for CVE-2026-34755?

Run the dependency tree command: 'pip show vllm'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.

Machine-readable OSV JSON OSV v1.5 Schema

Normalized schema output

View Raw JSON

{
  "schema_version" : "1.4.0",
  "id" : "GHSA-pq5c-rjhq-qp7p",
  "modified" : "2026-08-25T15:32:06Z",
  "published" : "2026-04-03T21:51:35Z",
  "aliases" : [ "CVE-2026-34755" ],
  "summary" : "vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing",
  "details" : "## Summary\n\nThe `VideoMediaIO.load_base64()` method at `vllm/multimodal/media/video.py:51-62` splits `video/jpeg` data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The `num_frames` parameter (default: 32), which is enforced by the `load_bytes()` code path at line 47-48, is completely bypassed in the `video/jpeg` base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM.\n\n## Details\n\n### Vulnerable code\n\n```python\n# video.py:51-62\ndef load_base64(self, media_type: str, data: str) -> tuple[npt.NDArray, dict[str, Any]]:\n    if media_type.lower() == \"video/jpeg\":\n        load_frame = partial(self.image_io.load_base64, \"image/jpeg\")\n        return np.stack(\n            [np.asarray(load_frame(frame_data)) for frame_data in data.split(\",\")]\n            #                                                       ^^^^^^^^^^\n            # Unbounded split — no frame count limit\n        ), {}\n    return self.load_bytes(base64.b64decode(data))\n```\n\nThe `load_bytes()` path (line 47-48) properly delegates to a video loader that respects `self.num_frames` (default 32). The `load_base64(\"video/jpeg\", ...)` path bypasses this limit entirely — `data.split(\",\")` produces an unbounded list and every frame is decoded into a numpy array.\n\n### video/jpeg is part of vLLM's public API\n\n`video/jpeg` is a vLLM-specific MIME type, not IANA-registered. However it is part of the public API surface:\n\n- `encode_video_url()` at `vllm/multimodal/utils.py:96-108` generates `data:video/jpeg;base64,...` URLs\n- Official test suites at `tests/entrypoints/openai/test_video.py:62` and `tests/entrypoints/test_chat_utils.py:153` both use this format\n\n### Memory amplification\n\nEach JPEG frame decodes to a full numpy array. For 640x480 RGB images, each frame is ~921 KB decoded. 5000 frames = ~4.6 GB. `np.stack()` then creates an additional copy. The compressed JPEG payload is small (~100 KB for 5000 frames) but decompresses to gigabytes.\n\n### Data flow\n\n```\nPOST /v1/chat/completions\n  → chat_utils.py:1434   video_url type → mm_parser.parse_video()\n  → chat_utils.py:872    parse_video() → self._connector.fetch_video()\n  → connector.py:295     fetch_video() → load_from_url(url, self.video_io)\n  → connector.py:91      _load_data_url(): url_spec.path.split(\",\", 1)\n                          → media_type = \"video/jpeg\"\n                          → data = \"<frame1>,<frame2>,...,<frame10000>\"\n  → connector.py:100     media_io.load_base64(\"video/jpeg\", data)\n  → video.py:54          data.split(\",\")  ← UNBOUNDED\n  → video.py:55-57       all frames decoded into numpy arrays\n  → video.py:56          np.stack([...])  ← massive combined array → OOM\n```\n\n`connector.py:91` uses `split(\",\", 1)` which splits on only the first comma. All remaining commas stay in `data` and are later split by `video.py:54`.\n\n### Comparison with existing protections\n\n| Code Path | Frame Limit | File |\n|-----------|-------------|------|\n| `load_bytes()` (binary video) | Yes — `num_frames` (default 32) | video.py:46-49 |\n| `load_base64(\"video/jpeg\", ...)` | No — unlimited `data.split(\",\")` | video.py:51-62 |",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "vllm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.7.0"
      }, {
        "fixed" : "0.19.0"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-34755"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/pull/38636"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395"
  }, {
    "type" : "WEB",
    "url" : "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/vllm-project/vllm"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-144.yaml"
  }, {
    "type" : "WEB",
    "url" : "https://bugzilla.redhat.com/show_bug.cgi?id=2455403"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/security/cve/CVE-2026-34755"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:59151"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:59144"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:57390"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:57389"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:57387"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:57380"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:36006"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:36005"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-770" ],
    "severity" : "MODERATE",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-04-03T21:51:35Z",
    "nvd_published_at" : "2026-04-06T16:16:36Z"
  }
}

CVSS V3

6.5 MODERATE

Attack Vector Network (AV:N)

Attack Complexity Low (AC:L)

Privileges Required Low (PR:L)

User Interaction None (UI:N)

Scope Unchanged (S:U)

Confidentiality None (C:N)

Integrity None (I:N)

Availability High (A:H)

Vector String

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Advisory Metadata

Source ID: GHSA-pq5c-rjhq-qp7p
Schema Version: 1.4.0
Published: 2026-04-03 21:51
Last Modified: 2026-08-25 15:32
Database Record File: advisories/github-reviewed/2026/04/GHSA-pq5c-rjhq-qp7p/GHSA-pq5c-rjhq-qp7p.json