Vulnerabilities in pkg:pypi/gpt-researcher

PACKAGE
Advisory Identifier: GHSA-8j86-h8gg-797p
Share
Advisory Summary

CVE-2025-65720 is a CRITICAL (CVSS 9.8) gpt researcher mcp stdio configuration vulnerability (CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')) affecting Gpt researcher libraries in the PyPI ecosystem. The issue involves gpt researcher mcp stdio configuration allows remote command execution. Remediation is available in the latest vendor maintenance releases.

1 Known Advisory Record(s)
Package Vulnerability Intelligence

pkg:pypi/gpt-researcher

1 Known Advisory Record(s)

Vulnerability advisories affecting package pkg:pypi/gpt-researcher. Select an advisory below to view technical details or fixes.

Advisory ID CVE / NVD Severity Summary
GHSA-8j86-h8gg-797p CVE-2025-65720 CRITICAL GPT Researcher MCP STDIO configuration allows remote command execution

CVE-2025-65720 at a Glance

CVE Identifier CVE-2025-65720
GHSA Identifier GHSA-8j86-h8gg-797p
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')
Affected Product Gpt researcher
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-2025-65720

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

gpt-researcher fixed: Latest secure release 
pip install gpt-researcher>=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 gpt-researcher

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2025-65720, inspect your installed packages using pip:

pip show gpt-researcher

Analyze the terminal output to locate any version of Gpt researcher 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 gpt-researcher command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection'), where the product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component. In Gpt researcher, 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

An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page.

CVE-2025-65720 Affected Gpt researcher Versions

1 component(s)
Product / Package Ecosystem Affected Versions Fixed Version
gpt-researcher
pypi/gpt-researcher
PyPI
≥ 0.14.5
≤ 0.14.7

References

NVD — CVE-2025-65720 NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-65720
Gpt researcher Source Repository REPOSITORY
https://github.com/assafelovic/gpt-researcher
Gpt researcher Security Information SECURITY
https://www.ox.security/blog/gpt-researcher-remote-code-execution
Gpt researcher Security Information SECURITY
https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem

Frequently Asked Questions

What is CVE-2025-65720?
CVE-2025-65720 is a security vulnerability in Gpt researcher involving GPT Researcher MCP STDIO configuration allows remote command execution under CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection').
Which Gpt researcher versions are affected?
Affected versions include releases prior to current release patches across affected packages: gpt-researcher.
What version fixes CVE-2025-65720?
Upgrading to current release patches (or the latest patched release for your respective branch) resolves the vulnerability.
Is gpt-researcher affected?
Yes, gpt-researcher 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-2025-65720?
CVE-2025-65720 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-2025-65720?
CVE-2025-65720 is classified under CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection') (The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.).
How can I check PyPI dependencies for CVE-2025-65720?
Run the dependency tree command: 'pip show gpt-researcher'. 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-8j86-h8gg-797p",
  "modified" : "2026-10-02T22:38:48Z",
  "published" : "2026-07-16T00:31:33Z",
  "aliases" : [ "CVE-2025-65720" ],
  "summary" : "GPT Researcher MCP STDIO configuration allows remote command execution",
  "details" : "An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page.",
  "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" : "gpt-researcher"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.14.5"
      }, {
        "last_affected" : "0.14.7"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2025-65720"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/assafelovic/gpt-researcher"
  }, {
    "type" : "WEB",
    "url" : "https://www.ox.security/blog/gpt-researcher-remote-code-execution"
  }, {
    "type" : "WEB",
    "url" : "https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-77" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-10-02T22:38:48Z",
    "nvd_published_at" : "2026-07-15T22:16:45Z"
  }
}