CVE-2026-31236: Llm Llm CLI Tool Contains A Vulnerability

CRITICAL
Advisory Identifier: GHSA-g76p-4vg5-f4qh
Share
CVSS 9.8
CWE-94
Published
Advisory Summary

CVE-2026-31236 is a CRITICAL (CVSS 9.8) llm cli tool contains a vulnerability (CWE-94: Improper Control of Generation of Code ('Code Injection')) affecting Llm libraries in the PyPI ecosystem. The issue involves llm cli tool contains a code injection vulnerability via `--functions` command-line argument. Remediation is available in the latest vendor maintenance releases.

CVE-2026-31236 at a Glance

CVE Identifier CVE-2026-31236
GHSA Identifier GHSA-g76p-4vg5-f4qh
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-94: Improper Control of Generation of Code ('Code Injection')
Affected Product Llm
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 9.8

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

How to Fix CVE-2026-31236

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

llm fixed: Latest secure release 
pip install llm>=Latest secure release
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 llm

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-31236, inspect your installed packages using pip:

pip show llm

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

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

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-94: Improper Control of Generation of Code ('Code Injection'), where the product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. In Llm, 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

The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control.

CVE-2026-31236 Affected Llm Versions

1 component(s)
Product / Package Ecosystem Affected Versions Fixed Version
llm
pypi/llm
PyPI
≤ 0.27.1

References

NVD — CVE-2026-31236 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-31236
Llm Source Repository REPOSITORY
https://github.com/simonw/llm
www.notion.so/cve-2026-31236-35d1... WEB
https://www.notion.so/CVE-2026-31236-35d1e139318881a4a0f1fffcf671f7e3

Frequently Asked Questions

What is CVE-2026-31236?
CVE-2026-31236 is a security vulnerability in Llm involving llm CLI tool contains a code injection vulnerability via `--functions` command-line argument under CWE-94: Improper Control of Generation of Code ('Code Injection').
Which Llm versions are affected?
Affected versions include releases prior to current release patches across affected packages: llm.
What version fixes CVE-2026-31236?
Upgrading to current release patches (or the latest patched release for your respective branch) resolves the vulnerability.
Is llm affected?
Yes, llm is affected in releases prior to Latest secure release. Upgrade your dependency to Latest secure release or later.
What is the CVSS score of CVE-2026-31236?
CVE-2026-31236 has a CVSS v3.1 base score of 9.8 (CRITICAL) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2026-31236?
CVE-2026-31236 is classified under CWE-94: Improper Control of Generation of Code ('Code Injection') (The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.).
How can I check PyPI dependencies for CVE-2026-31236?
Run the dependency tree command: 'pip show llm'. 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-g76p-4vg5-f4qh",
  "modified" : "2026-05-27T22:22:41Z",
  "published" : "2026-05-12T18:30:41Z",
  "aliases" : [ "CVE-2026-31236" ],
  "summary" : "llm CLI tool contains a code injection vulnerability via `--functions` command-line argument",
  "details" : "The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "llm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "last_affected" : "0.27.1"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-31236"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/simonw/llm"
  }, {
    "type" : "WEB",
    "url" : "https://www.notion.so/CVE-2026-31236-35d1e139318881a4a0f1fffcf671f7e3"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-94" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-05-27T22:22:41Z",
    "nvd_published_at" : "2026-05-12T18:16:51Z"
  }
}