Lucene search
+L

30 matches found

Snyk
Snyk
•added 2026/07/11 2:34 p.m.•25 views

Arbitrary Code Injection

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Arbitrary Code Injection via the CodeAgent.executepython function. An attacker can execute arbitrary code and exfiltrate environment secrets...

10CVSS6.5AI score0.1524EPSS
SaveExploits2References2
NVD
NVD
•added 2026/07/11 2:16 p.m.•32 views

CVE-2026-61447

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython 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...

10CVSS0.1524EPSS
SaveExploits2References2
CVE
CVE
•added 2026/07/11 1:01 p.m.•117 views

CVE-2026-61447

PraxionAI before 1.6.78 exposes a remote code execution flaw in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandboxing. This enables prompt-injection to exfiltrate environment secrets and run arbitrary code on the host. The v...

10CVSS6.9AI score0.1524EPSS
SaveExploits2References2
Mend
Mend
•added 2026/07/11 1:01 p.m.•14 views

CVE-2026-61447

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython 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...

10CVSS6.9AI score0.1524EPSS
SaveExploits2References4
attackerkb
attackerkb
•added 2026/07/11 1:01 p.m.•30 views

CVE-2026-61447

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython 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...

10CVSS6.9AI score0.1524EPSS
SaveExploits2References3
Cvelist
Cvelist
•added 2026/07/11 1:01 p.m.•81 views

CVE-2026-61447 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython 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...

10CVSS0.1524EPSS
SaveExploits2References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/07/11 12:00 a.m.•12 views

CVE-2026-61447: Improper Control of Generation of Code

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython 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...

10CVSS6.9AI score0.1524EPSS
SaveExploits2References2
Positive Technologies
Positive Technologies
•added 2026/07/11 12:00 a.m.•47 views

PT-2026-57440

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.6.78 Description A remote code execution issue exists in the CodeAgent. execute python function. The software executes Python code generated by a Large Language Model LLM without Abstract Syntax Tree AST validatio...

10CVSS7AI score0.1524EPSS
SaveExploits2References24
Positive Technologies
Positive Technologies
•added 2026/07/11 12:00 a.m.•5 views

PT-2026-108663

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-2xv2-w8cq-5gxw. This link is maintained to preserve external references. Original Description PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent. execute python that executes...

10CVSS6.8AI score0.1524EPSS
SaveExploits2References4
IBM Security Bulletins
IBM Security Bulletins
•added 2026/07/02 7:30 p.m.•55 views

Security Bulletin: Remote Code Execution in CUGA Component CodeAgent

Summary An authenticated user could execute arbitrary commands on the server when the CUGA component is installed and a flow using CUGA's CodeAgent is created and executed. The vulnerability exists in the CodeAgent's Python code execution path, which permits object graph introspection to recover...

9.9CVSS7.1AI score0.00632EPSS
SaveExploits0Affected Software1
Rows per page
Query Builder