praisonai vulnerabilities (npm)
10 vulnerabilities.
-
praisonainpm PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults 8.8 High -
praisonainpm PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining 8.8 High -
praisonainpm PraisonAI AgentLoop onToolCall approval runs after tool execution 8.8 High -
praisonainpm PraisonAI MCPServer exposes unauthenticated HTTP tools/call 9.8 Critical -
praisonainpm PraisonAI AgentOS exposes unauthenticated agent listing and invocation 9.4 Critical -
praisonainpm PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool 9.8 Critical -
praisonainpm PraisonAI SandboxExecutor allowedCommands bypass via shell chaining 8.8 High -
praisonainpm PraisonAI codeMode sandbox escape via Function constructor 9.9 Critical -
praisonainpm PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients 7.6 High -
praisonainpm PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation 8.2 High