CVE-2026-40289 PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessions

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the browser bridge praisonai browser start is vulnerable to unauthenticated remote session hijacking due to missing authentication and a bypassable origin check on its /ws WebSocket...

EUVD-2026-22211

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the browser bridge praisonai browser start is vulnerable to unauthenticated remote session hijacking due to missing authentication and a bypassable origin check on its /ws WebSocket...

EUVD-2026-22209

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run loads a YAML file with type: job, the...

CVE-2026-40288

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run loads a YAML file with type: job, the...

CVE-2026-40288 PraisonAI: Critical RCE via `type: job` workflow YAML

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run loads a YAML file with type: job, the...

CVE-2026-40288

PraisonAI and praisonaiagents prior to versions 4.5.139 and 1.5.140 are exposed to a critical RCE via untrusted workflow YAML. When a YAML file for type: job is loaded, the JobWorkflowExecutor (job_workflow.py) processes steps allowing run (subprocess.run), script (inline Python via exec), and py...

CVE-2026-40287

PraisonAI (versions 4.5.138 and earlier) is vulnerable to local arbitrary code execution via automatic, unsanitized import of a tools.py from the current working directory. The flaw arises in components such as call.py (import_tools_from_file()), tool_resolver.py (_load_local_tools()), and CLI to...

EUVD-2026-22207

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py importtoolsfromfile, toolresolver.py loadlocaltools, and CLI...

CVE-2026-40287 PraisonAI has RCE via Automatic tools.py Import

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py importtoolsfromfile, toolresolver.py loadlocaltools, and CLI...

CVE-2026-40287 PraisonAI has RCE via Automatic tools.py Import

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py importtoolsfromfile, toolresolver.py loadlocaltools, and CLI...

EUVD-2026-22215

PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the tableprefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization. Since SQL identifiers...

CVE-2026-40315

PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the tableprefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization. Since SQL identifiers...

CVE-2026-40315 PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queries

PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the tableprefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization. Since SQL identifiers...

CVE-2026-40315 PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queries

PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the tableprefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization. Since SQL identifiers...

CVE-2026-40315

CVE-2026-40315 affects PraisonAI’s SQLiteConversationStore where table_prefix is concatenated into SQL identifiers via f-strings, enabling attacker-controlled SQL injection. Connected documents show that the vulnerability originates from external-config input (from_yaml/from_dict) propagating thr...

CVE-2026-40114

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the /api/v1/runs endpoint accepts an arbitrary webhookurl in the request body with no URL validation. When a submitted job completes success or failure, the server makes an HTTP POST request to this URL using httpx.AsyncClient. An...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI 4.5.138 and earlier contained a security vulnerability. This vulnerability stemmed from the automatic and uncleanly import of the tools.py file from the current working directory, which...

PraisonAI 代码注入漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.139 and praisonaiagents prior to 1.5.140 contained a code injection vulnerability. This vulnerability stemmed from the workflow engine processing untrusted YAML files, which...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI 4.5.139 and earlier contained security vulnerabilities. These vulnerabilities stemmed from known credential exposure risks in GitHub Actions workflows, which could allow attackers to...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.133 contained security vulnerabilities, which were caused by SQL identifier injections in the SQLiteConversationStore. These vulnerabilities could lead to unauthorized data...