CVE-2026-57137 PraisonAI AgentLoop onToolCall approval runs after tool execution

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that...

CVE-2026-57141

PraisonAI (praisonai npm, a TypeScript multi-agent AI framework) is vulnerable to remote code execution via its codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts. The tool executes LLM-generated JavaScript using new Function() with a with(sandbox) pattern guarded by a regex blockl...

EUVD-2026-78423

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function and withsandbox, while a regular-expression blocklist can be bypassed with Function'return this' to recover the glob...

tamilai (0.0.2) potentially affected by CVE-2026-57141 via praisonai (1.7.1)

praisonai NPM version 1.7.1 is affected by a known vulnerability. The following packages have a transitive dependency on praisonai and may be impacted: - tamilai 0.0.2 Source cves: CVE-2026-57141 Source advisory: MEND:CVE-2026-57141...

CVE-2026-57141 PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function and withsandbox, while a regular-expression blocklist can be bypassed with Function'return this' to recover the glob...

CVE-2026-57141 PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function and withsandbox, while a regular-expression blocklist can be bypassed with Function'return this' to recover the glob...

CVE-2026-57141 PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function and withsandbox, while a regular-expression blocklist can be bypassed with Function'return this' to recover the glob...

CVE-2026-57112 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57112 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

EUVD-2026-78424

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57112 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57112

PraisonAI (multi-agent teams system) has a legacy SSE transport flaw in ToolsMCPServer.run_sse() (affecting praisonaiagents 0.6.0–1.6.58 and praisonai 3.10.0–4.6.58). The /sse and /messages/ endpoints lack Origin , Host , and authentication validation, unlike the newer Streamable HTTP transport w...

CVE-2026-57147: Use of Hard-coded Credentials

PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonaiplatform/services/authservice.py assigns the public dev-secret-change-me value to JWTSECRET when PLATFORMJWTSECRET is unset, and its production guard does not run when PLATFORMENV is also unset because that setting defaults to dev....

CVE-2026-57141: Improper Control of Generation of Code

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function and withsandbox, while a regular-expression blocklist can be bypassed with Function'return this' to recover the glob...

CVE-2026-57140: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the...

CVE-2026-57139: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest without authentication or authorization. Any network client that can reach the port can...

CVE-2026-57136: Improper Neutralization of Special Elements used in an OS Command

PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the first whitespace-delimited executable against allowedCommands, then SandboxExecutor passes the complete command string to sh -c. A command...

CVE-2026-57134: Improper Authentication

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without...

CVE-2026-57137: Protection Mechanism Failure

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that...

CVE-2026-57133: Improper Neutralization of Special Elements used in an OS Command

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to childprocess.exec. A string that starts...