Ghostwire

CVE-2026-61447: PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes...

CRITICAL CVSS 10.0 EPSS 0.54% Exploit Available 1 PoC

Published: July 11, 2026 | Last Modified: July 11, 2026

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.

Ghostwire Analysis — What This Means Practically

Exploitation Probability (EPSS): Low — 0.54% (42th percentile)

Low exploitation probability based on current threat landscape data. Standard patching timeline is appropriate.

Critical CVSS score indicates maximum severity — remote code execution, authentication bypass, or complete system compromise is likely possible.
1 proof-of-concept exploit available on GitHub. Public exploit code lowers the barrier for both researchers and attackers.

This analysis is generated by Ghostwire from NVD, CISA KEV, EPSS, and open-source intelligence data. Verify findings through primary sources before acting.

Proof-of-Concept Exploits (1)

MervinPraison/PraisonAI

CVE-2026-61447: PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes...

Description

Ghostwire Analysis — What This Means Practically

Proof-of-Concept Exploits (1)

Security Coverage (1 articles)

References