Lucene search
+L

2 matches found

GithubExploit
GithubExploit
added 2026/06/01 10:12 a.m.110 views

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

6.5AI score
SaveExploits0
ATTACKERKB
ATTACKERKB
added 2026/04/09 7:45 p.m.6 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 score0.00419EPSS
SaveExploits1References3Affected Software1
Rows per page
Query Builder