Lucene search
+L

8 matches found

NVD
NVD
•added 2026/10/23 12:18 p.m.•15 views

CVE-2026-56838

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

7.8CVSS0.00146EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/10/23 11:58 a.m.•31 views

CVE-2026-56838 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

7.8CVSS0.00146EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
•added 2026/10/23 11:58 a.m.•12 views

CVE-2026-56838 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

7.8CVSS5.8AI score0.00146EPSS
SaveExploits0References1
osv_cve
osv_cve
•added 2026/10/23 11:58 a.m.•22 views

CVE-2026-56838 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

7.8CVSS5.8AI score
SaveExploits0References3
CVE
CVE
•added 2026/10/23 11:58 a.m.•52 views

CVE-2026-56838

PraisonAI versions 4.5.87 through 4.6.57 are vulnerable to a policy enforcement bypass in the recipe.run_stream() function. While the standard recipe.run() path correctly invokes _check_tool_policy() to block dangerous tools unless allow_dangerous_tools=True is specified, the streaming path calls...

7.8CVSS5.8AI score0.00146EPSS
SaveExploits0References1
EUVD
EUVD
•added 2026/10/23 11:58 a.m.•23 views

EUVD-2026-108879

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

7.8CVSS5.8AI score0.00146EPSS
SaveExploits0References1
CNNVD
CNNVD
•added 2026/10/23 12:00 a.m.•17 views

Mervin Praison PraisonAI processing logic error vulnerability

A security vulnerability exists in Mervin Praison PraisonAI versions from 4.5.87 up to and including 4.6.59. This vulnerability arises because the recipe.runstream stream execution path fails to perform checks on dangerous tools, allowing recipes declared as executecommand to bypass restrictions ...

7.8CVSS6.2AI score0.00146EPSS
SaveExploits0References1
Mend
Mend
•added 2026/07/20 11:35 p.m.•15 views

CVE-2026-56838

PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes "allowdangeroustools=True". The normal "recipe.run" path enforces this with "checktoolpolicy". The streaming path, "recipe.runstream", loads the same recipe, checks dependencies, and then calls...

8.5CVSS5.9AI score0.00146EPSS
SaveExploits0References5
Rows per page
Query Builder