PraisonAI has RCE via Automatic tools.py Import_CVE-2026-40287

8.4 / 10

HIGH

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

Description

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py (import_tools_from_file()), tool_resolver.py (_load_local_tools()), and CLI tool-loading paths blindly import ./tools.py at startup without any validation, sandboxing, or user confirmation. An attacker who can place a malicious tools.py in the directory where PraisonAI is launched (such as through a shared project, cloned repository, or writable workspace) achieves immediate arbitrary Python code execution in the host environment. This compromises the full PraisonAI process, the host system, and any connected data or credentials. This issue has been fixed in version 4.5.139.

Basic Information

ID CVE-2026-40287

Source GitHub_M

Published Apr 14, 2026 at 02:55

Affected Product

Vendor MervinPraison

Product PraisonAI

Version < 4.5.139

Affected Versions MervinPraison PraisonAI < 4.5.139
MervinPraison praisonaiagents < 1.5.140

CWE Classification

CWE-94 CWE-426

References

github.com /MervinPraison/PraisonAI/security/advisories/GHSA-g985-wjh9-qxxc

{
    "lastseen": "",
    "description": "PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py (import_tools_from_file()), tool_resolver.py (_load_local_tools()), and CLI tool-loading paths blindly import ./tools.py at startup without any validation, sandboxing, or user confirmation. An attacker who can place a malicious tools.py in the directory where PraisonAI is launched (such as through a shared project, cloned repository, or writable workspace) achieves immediate arbitrary Python code execution in the host environment. This compromises the full PraisonAI process, the host system, and any connected data or credentials. This issue has been fixed in version 4.5.139.",
    "published": "2026-04-14T02:55:38.270Z",
    "modified": "2026-04-14T02:55:38.270Z",
    "type": "cve",
    "title": "PraisonAI has RCE via Automatic tools.py Import",
    "source": "GitHub_M",
    "references": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-g985-wjh9-qxxc",
    "id": "CVE-2026-40287",
    "bulletinFamily": "",
    "cwe": [
        "CWE-94",
        "CWE-426"
    ],
    "cvelist": null,
    "sourceData": "MervinPraison PraisonAI < 4.5.139\nMervinPraison praisonaiagents < 1.5.140",
    "sourceHref": "",
    "cvss": {
        "score": 8.4,
        "severity": "HIGH",
        "vector": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
        "version": "3.1"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "",
    "category_name": "CVE",
    "post_link": "",
    "product": "PraisonAI",
    "version": "< 4.5.139",
    "vendor": "MervinPraison",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}