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...

EUVD-2026-65500

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-2026-78250

A vulnerability was identified in bytebot-ai bytebot 0.0.1. The affected element is an unknown function of the component Agent Execution Workflow. Such manipulation leads to infinite loop. The attack may be performed from remote. The exploit is publicly available and might be used. This...

CVE-2026-78250

bytebot-ai bytebot 0.0.1 is affected by a vulnerability in the Agent Execution Workflow component where manipulation of an unknown function leads to an infinite loop , resulting in a denial of service (availability impact only). The attack can be performed remotely and requires low privileges (CV...

EUVD-2026-64854

A vulnerability was identified in bytebot-ai bytebot 0.0.1. The affected element is an unknown function of the component Agent Execution Workflow. Such manipulation leads to infinite loop. The attack may be performed from remote. The exploit is publicly available and might be used. This...

CVE-2026-61613

Cursor is a code editor built for programming with AI. Prior to the Cloud Agent fix on 03/31/2026, browser-enabled Cursor Cloud Agent sessions allowed attacker-controlled web content to connect from inside the agent container to an unauthenticated local agent endpoint, enabling code execution...

CVE-2026-56076

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: headers, combined with Starlette's...

CVE-2026-56076 PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: headers, combined with Starlette's...

GHSA-FQ2M-6WQH-X44G PraisonAI: Jobs API exposes agent-execution endpoints with no authentication

praisonai: Jobs API exposes agent-execution endpoints with no authentication Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Target: https://github.com/MervinPraison/PraisonAI --- Package: praisonai on PyPI Affected version empirically tested: 4.6.48...

PT-2026-50807

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.5.128 Description A cross-origin agent execution issue exists in the 'POST /agui' endpoint, allowing remote attackers to trigger arbitrary agent execution. The endpoint lacks authentication and utilizes hardcoded...

CVE-2026-6612

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function getagentexecution/updateagentexecution of the file superagi/controllers/agentexecution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agentexecutionid can...

CVE-2026-6612

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function getagentexecution/updateagentexecution of the file superagi/controllers/agentexecution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agentexecutionid can...

CVE-2026-6612

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function getagentexecution/updateagentexecution of the file superagi/controllers/agentexecution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agentexecutionid can...

CVE-2026-6612

The vulnerability CVE-2026-6612 affects TransformerOptimus SuperAGI up to version 0.0.14, specifically the Agent Execution Endpoint’s get_agent_execution/update_agent_execution in superagi/controllers/agent_execution.py. The underlying issue is an authorization bypass caused by manipulating the a...

CVE-2026-6612 TransformerOptimus SuperAGI Agent Execution Endpoint agent_execution.py update_agent_execution authorization

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function getagentexecution/updateagentexecution of the file superagi/controllers/agentexecution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agentexecutionid can...

CVE-2026-6612 TransformerOptimus SuperAGI Agent Execution Endpoint agent_execution.py update_agent_execution authorization

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function getagentexecution/updateagentexecution of the file superagi/controllers/agentexecution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agentexecutionid can...

SuperAGI 安全漏洞

SuperAGI is an open-source infrastructure application developed by SuperAGI. It is used to build components, tools, frameworks, and models to achieve open-source AGI. Versions of SuperAGI 0.0.14 and earlier contain security vulnerabilities. These vulnerabilities stem from incorrect operations wit...

PT-2026-33719

A vulnerability was determined in TransformerOptimus SuperAGI up to 0.0.14. This impacts the function get agent execution/update agent execution of the file superagi/controllers/agent execution.py of the component Agent Execution Endpoint. Executing a manipulation of the argument agent execution ...

EUVD-2026-22941

LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execution handling. A remote attacker can access the publicly exposed MCP management interface and configure an MCP STDIO server with attacker-controlled commands and arguments. When...

CVE-2026-30617

LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execution handling. A remote attacker can access the publicly exposed MCP management interface and configure an MCP STDIO server with attacker-controlled commands and arguments. When...