Lucene search
+L

1 matches found

Github Security Blog
Github Security Blog
added 2026/04/08 7:21 p.m.29 views

PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling

Summary The MultiAgentLedger and MultiAgentMonitor components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically: 1. Memory State Leakage via Agent ID Collision: The MultiAgentLedger uses a dictionary to store ledgers by agent...

8.8CVSS6.6AI score0.00915EPSS
SaveExploits0References4Affected Software1
Rows per page
Query Builder