CVE-2026-0599: Text generation Remote Code Execution Vulnerability

HIGH
Advisory Identifier: GHSA-j7x9-7j54-2v3h
Share
CVSS 7.5
CWE-400
Published
Advisory Summary

CVE-2026-0599 is a HIGH (CVSS 7.5) remote code execution vulnerability (CWE-400: Uncontrolled Resource Consumption) affecting Text generation libraries in the PyPI ecosystem. The issue involves hugging face text generation inference vulnerable to uncontrolled resource consumption. Remediation is available by upgrading affected packages to version 3.3.7.

CVE-2026-0599 at a Glance

CVE Identifier CVE-2026-0599
GHSA Identifier GHSA-j7x9-7j54-2v3h
Severity HIGH
CVSS v3.1 Base Score 7.5
CWE Classification CWE-400: Uncontrolled Resource Consumption
Affected Product Text generation
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 7.5

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
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-2026-0599

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

text-generation fixed: 3.3.7 
pip install text-generation>=3.3.7
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 text-generation

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-0599, inspect your installed packages using pip:

pip show text-generation

Analyze the terminal output to locate any version of Text generation in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 3.3.7), your application is affected.

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

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-400: Uncontrolled Resource Consumption, where the product does not properly control the allocation and maintenance of a limited resource. In Text generation, 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

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.

CVE-2026-0599 Affected Text generation Versions

1 component(s)
Fixed Versions:
3.3.7
Product / Package Ecosystem Affected Versions Fixed Version
text-generation
pypi/text-generation
PyPI
< 3.3.7
3.3.7

References

NVD — CVE-2026-0599 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-0599
Security Fix Commit FIX COMMIT
https://github.com/huggingface/text-generation-inference/commit/24ee40d143d8d046039f12f76940a85886cbe152
Text generation Source Repository REPOSITORY
https://github.com/huggingface/text-generation-inference
huntr.com/bounties/1d3f2085-6... WEB
https://huntr.com/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd

Frequently Asked Questions

What is CVE-2026-0599?
CVE-2026-0599 is a security vulnerability in Text generation involving Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption under CWE-400: Uncontrolled Resource Consumption.
Which Text generation versions are affected?
Affected versions include releases prior to 3.3.7 across affected packages: text-generation.
What version fixes CVE-2026-0599?
Upgrading to 3.3.7 (or the latest patched release for your respective branch) resolves the vulnerability.
Is text-generation affected?
Yes, text-generation is affected in releases prior to 3.3.7. Upgrade your dependency to 3.3.7 or later.
What is the CVSS score of CVE-2026-0599?
CVE-2026-0599 has a CVSS v3.1 base score of 7.5 (HIGH) with vector string CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
What CWE is associated with CVE-2026-0599?
CVE-2026-0599 is classified under CWE-400: Uncontrolled Resource Consumption (The product does not properly control the allocation and maintenance of a limited resource.).
How can I check PyPI dependencies for CVE-2026-0599?
Run the dependency tree command: 'pip show text-generation'. 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-j7x9-7j54-2v3h",
  "modified" : "2026-02-02T22:07:41Z",
  "published" : "2026-02-02T12:31:14Z",
  "aliases" : [ "CVE-2026-0599" ],
  "summary" : "Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption",
  "details" : "A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "text-generation"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "3.3.7"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-0599"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/huggingface/text-generation-inference/commit/24ee40d143d8d046039f12f76940a85886cbe152"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/huggingface/text-generation-inference"
  }, {
    "type" : "WEB",
    "url" : "https://huntr.com/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-400" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-02-02T22:07:41Z",
    "nvd_published_at" : "2026-02-02T11:16:17Z"
  }
}