Lucene search
+L

2 matches found

Mend
Mend
•added 2026/04/09 7:45 p.m.•14 views

CVE-2026-40088

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell...

9.6CVSS6.2AI score0.00426EPSS
SaveExploits1References7
CNNVD
CNNVD
•added 2026/04/09 12:00 a.m.•30 views

PraisonAI operating system command injection vulnerability

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.121 contained a vulnerability related to operating system command injection. This vulnerability stemmed from the executecommand function and the workflow shell, which expose...

9.6CVSS6.9AI score0.00426EPSS
SaveExploits1References2
Rows per page
Query Builder