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.
CVSS breakdown
CVSS 4.0
Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Confidentiality (Vulnerable System)
High
Integrity (Vulnerable System)
High
Availability (Vulnerable System)
High
Confidentiality (Subsequent System)
High
Integrity (Subsequent System)
High
Availability (Subsequent System)
High
CVSS 3.1
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High
Affected products
- MervinPraison / PraisonAI0 – 1.6.78
- MervinPraison / PraisonAI1.6.78 – 1.6.78
Exploits & proofs of concept
- exploit-dbPraisonAI praisonaiagents 1.6.77 - Remote Code Executionby banyamer
Updated 14m ago · 8 sources