CVE-2026-55536 Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, Browser Server handleconnection checks Chrome extension origins with re.match and the unanchored expression chrome-extension://a-z0-932. Extra trailing characters pass before websocket.accept, allowing startsession commands and...

GHSA-PVPH-5J39-V8QC PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

Summary The PraisonAI MCP server exposes an HTTP-stream transport praisonai mcp serve --transport http-stream that binds to localhost and, by default, has no API key. Its only access control for browser-originated requests is an Origin allowlist, which the code implements as required by the MCP...

PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

Summary The PraisonAI MCP server exposes an HTTP-stream transport praisonai mcp serve --transport http-stream that binds to localhost and, by default, has no API key. Its only access control for browser-originated requests is an Origin allowlist, which the code implements as required by the MCP...

Cross-site Request Forgery (CSRF)

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

CVE-2026-55532 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

CVE-2026-55532 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

CVE-2026-55532

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

CVE-2026-55532

PraisonAI is a multi-agent teams system. Prior to version 4.6.58 , the MCP HTTP Stream _validate_origin function uses request_origin.startswith(allowed), which allows an attacker-controlled origin such as localhost.attacker.com to satisfy a localhost allowlist entry. This enables an unauthenticat...

CVE-2026-55532 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

EUVD-2026-65544

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

CVE-2026-55531

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcppost handler creates a new sessions entry for every initialize request but does not call cleanupsessions or enforce a maximum. An unauthenticated caller can exhaust memory. The fix invokes cleanup and limit...

CVE-2026-55534

PraisonAI is a multi-agent teams system. From praisonai 4.6.34 until 4.6.58, praisonai serve agents accepts --api-key but createagentsapp does not authenticate POST /agents or POST /agents/agentname. A network caller can invoke configured agents without credentials even when an API key was...

CVE-2026-55537

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validatewebhookurl accepts webhookurl when resolution raises socket.gaierror because the exception path uses except socket.gaierror: pass. JobExecutor.sendwebhook later performs a fresh lookup, allowing DNS chang...

CVE-2026-55535

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the Jobs API validatewebhookurl path fails open on socket.gaierror and does not bind the validated address to the later request. An attacker webhookurl can later resolve to 127.0.0.1, 169.254.169.254, or another internal address...

CVE-2026-55538

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, praisonai serve agents parses config"apikey" but createagentsapp does not authenticate POST /agents or POST /agents/agentname. Missing or incorrect bearer and X-API-Key values still reach agent execution. This issue is fixed in...

CVE-2026-55540

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, ispathwithindirectory uses os.path.abspath rather than os.path.realpath for the workspace boundary. A symlink inside workspace can point outside and still pass the check, allowing readfile and other code tools to access files...

CVE-2026-55541

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve unified parse --api-key but createagentsapp and createunifiedapp do not install a credential check. Unauthenticated callers can reach POST /agents and POST /api/v1/agents/id/invoke. This...

CVE-2026-55526

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, spidertools.hostisblocked does not resolve ordinary hostnames before scrapepage fetches them. A hostname such as 127.0.0.1.nip.io passes validation and resolves to loopback, permitting internal HTTP access. The fix uses...

CVE-2026-55527

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the FileMemory constructor joins unsanitized userid into self.userpath. A caller supplying ../ or path separators can escape the memory directory and write JSON data to arbitrary process-writable locations. The fix sanitize...

CVE-2026-55528

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, AgentServer exposes ServerConfig.authtoken but AgentServer.createapp does not check it on any route. A remote caller can subscribe, publish, and perform other actions without a valid bearer token or X-Auth-Token even when...