PraisonAI: Unauthenticated Local File Inclusion via agent_file path in PraisonAI Jobs API

SummaryAn unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the agentfile field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. DetailsThe agentfile field in JobSubmitReque...

PYSEC-2026-3536 PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired in

The MCP SSE server started via ToolsMCPServer.runsse / launchtoolsmcpservertransport="sse" binds to 0.0.0.0 by default and builds its Starlette application with no authentication middleware and no Origin-header validation. The module mcp/mcpsecurity.py provides exactly the needed controls origin...

PYSEC-2026-3521 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools Summary praisonaiagents.mcp.ToolsMCPServer.runsse builds a Starlette MCP HTTP+SSE server around mcp.server.sse.SseServerTransport. The server exposes /sse and /messages/, but it does not valida...

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,...

PYSEC-2026-3502 PraisonAI recipe serve Typer command bypasses the non-localhost authentication guard

PraisonAI recipe serve Typer command bypasses the non-localhost authentication guard Summary PraisonAI's installed console entrypoint is Typer-first. In current releases, the recipe command is registered in the Typer app and praisonai recipe serve dispatches to the deprecated Typer command in...

PYSEC-2026-3514 PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage

PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage Summary PraisonAI's Dynamic Context Discovery feature exposes artifact helper tools through ctx.gettools: python ctx = setupdynamiccontext agent = Agent instructions="You are a data analyst.",...

PYSEC-2026-3522 PraisonAI: Compute-bridged file tools allow shell command injection

Compute-bridged file tools allow shell command injection Summary LocalManagedAgent / SandboxedAgent compute bridging wraps readfile, listfiles, and writefile when a compute provider is attached. The bridge converts those file operations into shell command strings using raw path arguments, then...

PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage

PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage SummaryPraisonAI's Dynamic Context Discovery feature exposes artifact helper toolsthrough ctx.gettools:pythonctx = setupdynamiccontextagent = Agent instructions="You are a data analyst.", tools=ctx.gettool...

PYSEC-2026-3499 PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal

PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal Summary PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing: - artifact storage for tool...

PYSEC-2026-3510 PraisonAI LinearBot processes unsigned webhooks when LINEAR_WEBHOOK_SECRET is missing

PraisonAI LinearBot processes unsigned webhooks when LINEARWEBHOOKSECRET is missing Summary PraisonAI's LinearBot starts a public webhook listener on 0.0.0.0 and treats LINEARWEBHOOKSECRET as optional. When the secret is absent, startup only logs a warning and handlewebhook skips Linear-Signature...

PraisonAI Slack app_mention bypasses configured user/channel authorization

PraisonAI Slack appmention bypasses configured user/channel authorization SummaryPraisonAI's Slack bot applies its configured allowedusers,allowedchannels, and unknown-user pairing policy in the normal Slackmessage event handler, but not in the adjacent Slack appmention eventhandler.A Slack...

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...

PYSEC-2026-3534 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools Summary praisonaiagents.mcp.ToolsMCPServer.runsse builds a Starlette MCP HTTP+SSE server around mcp.server.sse.SseServerTransport. The server exposes /sse and /messages/, but it does not valida...

PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals

DiscordApproval accepts unrelated channel messages as dangerous-tool approvals Summarypraisonai.bots.DiscordApproval approves a pending dangerous tool call when itsees any later non-bot message in the configured Discord channel whose text isclassified as approval, such as yes.The decision is not...

PT-2026-64107

PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal Summary PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing: - artifact storage for tool...

PT-2026-64122

Jobs webhook SSRF protection bypass via DNS rebinding Summary PraisonAI's Async Jobs API validates webhook url when a job request is parsed and again when the internal Job object is constructed. That validation blocks direct loopback/private targets, but it is not bound to the later network...

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,...

PT-2026-64110

PraisonAI recipe serve Typer command bypasses the non-localhost authentication guard Summary PraisonAI's installed console entrypoint is Typer-first. In current releases, the recipe command is registered in the Typer app and praisonai recipe serve dispatches to the deprecated Typer command in...

PT-2026-64108

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

PT-2026-64137

PraisonAI AgentTeam.launch exposes unauthenticated remote agent invocation endpoints Summary PraisonAI's documented Python AgentTeam.launch / Agents.launch HTTP server starts externally reachable agent invocation endpoints without any authentication enforcement. The current implementation registe...