Lucene search
+L

6 matches found

NVD
NVD
added 2026/07/23 6:17 p.m.10 views

CVE-2026-65699

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target runid in the request body without ownership verification. The AgentCRUD.createtask and...

4.2CVSS0.00222EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2026/07/23 4:59 p.m.11 views

CVE-2026-65699 AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target runid in the request body without ownership verification. The AgentCRUD.createtask and...

4.2CVSS5.3AI score0.00222EPSS
SaveExploits0References2
ATTACKERKB
ATTACKERKB
added 2026/07/23 4:59 p.m.12 views

CVE-2026-65699

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target runid in the request body without ownership verification. The AgentCRUD.createtask and...

4.2CVSS5.3AI score0.00222EPSS
SaveExploits0References3
OSV
OSV
added 2026/07/21 3:21 p.m.12 views

CVE-2026-47391 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

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...

9.8CVSS6AI score
SaveExploits0References5
CVE
CVE
added 2026/07/21 3:21 p.m.100 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...

9.8CVSS6AI score0.0078EPSS
SaveExploits0References3
Cvelist
Cvelist
added 2026/07/21 3:21 p.m.27 views

CVE-2026-47391 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

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...

9.8CVSS0.0078EPSS
SaveExploits0References3
Rows per page
Query Builder