Lucene search
+L

3 matches found

Positive Technologies
Positive Technologies
•added 2026/07/23 12:00 a.m.•34 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 score
SaveExploits0References6
osv_ghsa
osv_ghsa
•added 2026/06/18 2:26 p.m.•32 views

GHSA-7QW2-W5RC-37X2 PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

Summary 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 TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path...

7.8CVSS6AI score
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/06/18 12:00 a.m.•22 views

PT-2026-53128

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...

7.8CVSS6AI score
SaveExploits0References3
Rows per page
Query Builder