עברית

Vulnerability Intelligence

CVE-2026-61447

Critical 10.0

Published
Last modified
NVD status
Deferred

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.

References3

Metrics

CVSS 3.1
10.0 CRITICAL Score source: CNA CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
CVSS 4.0
10.0 CRITICAL Score source: 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS — exploit probability
15% percentile: 97 · as of 15 November 2026
CWE
CWE-94

Could this be exploited in your environment?

A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.