Lucene search
+L

29 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
Vulnrichment
Vulnrichment
•added 2026/10/23 12:07 p.m.•13 views

CVE-2026-57142 PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in...

7.8CVSS5.8AI score0.0024EPSS
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
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
Vulnrichment
Vulnrichment
•added 2026/10/23 11:55 a.m.•12 views

CVE-2026-56832 PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

PraisonAI is a multi-agent teams system. From version 4.5.2 to before version 4.6.59, praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. As a result, any...

8.8CVSS6AI score0.00148EPSS
SaveExploits0References1
osv_cve
osv_cve
•added 2026/10/23 11:55 a.m.•21 views

CVE-2026-56832 PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

PraisonAI is a multi-agent teams system. From version 4.5.2 to before version 4.6.59, praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. As a result, any...

8.8CVSS6AI score0.00148EPSS
SaveExploits0References3
CVE
CVE
•added 2026/10/23 11:55 a.m.•39 views

CVE-2026-56832

The PraisonAI multi-agent system (versions 4.5.2 through 4.6.58 ) contains an incorrect authorization vulnerability in its DiscordApproval backend. The praisonai.bots.DiscordApproval component improperly handles tool call approvals by polling the configured Discord channel for any non-bot message...

8.8CVSS6AI score0.00148EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/10/23 11:55 a.m.•37 views

CVE-2026-56832 PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

PraisonAI is a multi-agent teams system. From version 4.5.2 to before version 4.6.59, praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. As a result, any...

8.8CVSS0.00148EPSS
SaveExploits0References1
PyPA
PyPA
•added 2026/07/23 11:41 a.m.•67 views

PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

SummaryPraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools.For steps-based recipes, the actual execution path load...

7.8CVSS5.9AI score0.0024EPSS
SaveExploits0References5Affected Software1
osv_pysec
osv_pysec
•added 2026/07/23 11:41 a.m.•42 views

PYSEC-2026-3520 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI recipe.runstream skips dangerous-tool policy enforcement Summary 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,...

7.8CVSS6.1AI score0.00146EPSS
SaveExploits0References5
PyPA
PyPA
•added 2026/07/23 11:41 a.m.•63 views

PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI recipe.runstream skips dangerous-tool policy enforcement SummaryPraisonAI recipe execution blocks default-denied dangerous tools unless thecaller explicitly passes allowdangeroustools=True. The normal recipe.runpath enforces this with checktoolpolicy. The streaming path,recipe.runstream...

7.8CVSS6.1AI score0.00146EPSS
SaveExploits0References5Affected Software1
Positive Technologies
Positive Technologies
•added 2026/07/23 12:00 a.m.•37 views

PT-2026-64123

PraisonAI recipe.run stream skips dangerous-tool policy enforcement Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow dangerous tools=True. The normal recipe.run path enforces this with check tool policy. The streaming path,...

7.8CVSS6.3AI score0.00146EPSS
SaveExploits0References6
Positive Technologies
Positive Technologies
•added 2026/07/23 12:00 a.m.•46 views

PT-2026-64112

Summary PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow dangerous tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path...

7.8CVSS6.2AI score0.0024EPSS
SaveExploits0References6
Positive Technologies
Positive Technologies
•added 2026/07/23 12:00 a.m.•30 views

PT-2026-64113

DiscordApproval accepts unrelated channel messages as dangerous-tool approvals Summary praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. The decision is...

8.8CVSS6.4AI score0.00148EPSS
SaveExploits0References6
Github Security Blog
Github Security Blog
•added 2026/06/18 1:52 p.m.•32 views

PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

DiscordApproval accepts unrelated channel messages as dangerous-tool approvals Summary praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. The decision is...

6.2AI score0.00148EPSS
SaveExploits0References2Affected Software1
osv_ghsa
osv_ghsa
•added 2026/06/18 1:52 p.m.•48 views

GHSA-8579-RGG5-PH2M PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

DiscordApproval accepts unrelated channel messages as dangerous-tool approvals Summary praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. The decision is...

8.8CVSS6.2AI score0.00148EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/06/18 12:00 a.m.•32 views

PT-2026-61757

Name of the Vulnerable Software and Affected Versions praisonai versions 4.5.2 through 4.6.58 Description The praisonai.bots.DiscordApproval component improperly handles approval requests for dangerous tool calls. It approves a pending request if any non-bot message containing approval text, such...

8.8CVSS6AI score0.00148EPSS
SaveExploits0References7
Positive Technologies
Positive Technologies
•added 2026/06/18 12:00 a.m.•33 views

PT-2026-53129

DiscordApproval accepts unrelated channel messages as dangerous-tool approvals Summary praisonai.bots.DiscordApproval approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval, such as yes. The decision is...

8.8CVSS5.9AI score
SaveExploits0References3
Rows per page
Query Builder