Back to overview

CVE-2026-61447

CRITICAL
10.0
CVSS 3.1
Description
PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Metadata

CVE ID
CVE-2026-61447
State
PUBLISHED
Assigner
VulnCheck
Reserved
2026-07-09 14:06 UTC
Published
2026-07-11 13:01 UTC
Last updated
2026-07-11 13:01 UTC
Primary CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')
Vendor / Product
MervinPraison / PraisonAI
Sources
cve.org  ·  NVD

Severity & Metrics

10.0 CRITICAL CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Affected products (1)
VendorProductPlatformVersions
MervinPraison PraisonAI 0 < 1.6.78, 1.6.78
Weakness (CWE)
CWESourceDescription
CWE-94 cna Improper Control of Generation of Code ('Code Injection')
CVSS scores (2)
ScoreSeverityVersionSourceVector
10.0 CRITICAL 4.0 cna CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
10.0 CRITICAL 3.1 cna CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
References (2)
Back to overview