Shopper: Authorization bypass in Filament bulk actions allows browse-only staff to mass-delete attributes/tags and mass-toggle visibility of brands/categories/suppliers

Summary Five Filament groupedBulkActions blocks across the Shopper admin Livewire pages omit the -authorize... permission gate, while their per-record sibling actions and other Shopper Index pages such as Pages/Settings/Currencies.php, Pages/Reviews/Index.php, Pages/Collection/Index.php, and...

EUVD-2026-74932

Snipe-IT versions 4.2.0 through 8.6.3 expose Laravel Passport's auto-registered personal-access-token routes GET, POST, DELETE /oauth/personal-access-tokens with only 'web' and 'auth:web' middleware, without the self.api permission gate that Snipe-IT enforces on its own token endpoints /account/a...

PYSEC-2026-2948 PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Summary praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An...

PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Summary praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An...

GHSA-GMJG-HV98-QGGQ PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Summary praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An...

CVE-2026-44339

PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration,...

PT-2026-39006

Name of the Vulnerable Software and Affected Versions praisonai versions prior to 4.6.37 praisonaiagents versions prior to 1.6.37 Description PraisonAI is a multi-agent teams system. The praisonaiagents component resolves unresolved tool names against module globals and main after failing to matc...

Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode

Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation o...