Lucene search
+L

3 matches found

EUVD
EUVD
•added 2026/07/21 3:21 p.m.•40 views

EUVD-2026-46281

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a calculateexpression tool implemented with Python eval. The example also binds to 0.0.0.0. A remote unauthenticated attacker...

9.8CVSS6.2AI score0.01165EPSS
SaveExploits0References3
CVE
CVE
•added 2026/07/21 3:21 p.m.•125 views

CVE-2026-47391

PraisonAI’s first-party A2A example exposes an unauthenticated /a2a JSON-RPC surface and registers a calculate(expression) tool implemented via Python eval(), bound to 0.0.0.0. A remote attacker can send message/send to a2a, causing the LLM to invoke the unsafe tool and potentially execute arbitr...

9.8CVSS6.2AI score0.01165EPSS
SaveExploits0References3
PyPA
PyPA
•added 2026/06/29 11:50 a.m.•28 views

PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

SummaryThe first-party PraisonAI A2A server example combines three behaviors into a remotely exploitable Critical chain:1. The example exposes an A2A server without configuring authtoken.2. The same example binds the server to 0.0.0.0.3. The example registers a calculateexpression tool implemente...

9.8CVSS6.7AI score0.01165EPSS
SaveExploits0References5Affected Software1
Rows per page
Query Builder