Lucene search
K

427 matches found

CNNVD
CNNVD
added 2026/04/09 12:0 a.m.5 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the WSGI server not setting an upper limit when reading HTTP request bodies and disabling...

7.5CVSS5.8AI score0.00334EPSS
Exploits1References2
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.6 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the lack of authentication or signature verification for the /media-stream WebSocket endpoint, alo...

7.5CVSS5.8AI score0.00372EPSS
Exploits1References2
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.3 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the safeextractall function not checking the size, cumulative size, or quantity of archived files...

6.5CVSS5.8AI score0.00243EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.4 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 1.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the readskillfile function accepting an unlimited skillpath parameter, which could allow agents to...

7.5CVSS5.8AI score0.00234EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.5 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the/api/approval/allow-list endpoint, which unauthenticated modifications to the tool approval...

7.9CVSS5.8AI score0.00227EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.4 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained security vulnerabilities. These vulnerabilities stemmed from treating remotely obtained template files as trusted executable code without performing integrity...

9.6CVSS5.9AI score0.00304EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.3 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 1.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the executecommand function manually expanding environment variables, which could lead to the...

7.4CVSS5.8AI score0.00273EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.4 views

PraisonAI 信息泄露漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained an information leakage vulnerability. This vulnerability stemmed from the AgentOS deployment platform not implementing authentication, and the default CORS...

5.3CVSS5.8AI score0.00594EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/04/09 12:0 a.m.4 views

PraisonAI 跨站脚本漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.128 contained a cross-site scripting vulnerability. This vulnerability stemmed from Flask API endpoints rendering HTML, where cleanup operations were ineffective, allowing...

6.1CVSS5.8AI score0.00216EPSS
Exploits1References2
Positive Technologies
Positive Technologies
added 2026/04/09 12:0 a.m.1 views

PT-2026-31786

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, read skill file in skill tools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skill path parameter. Unlike file tools.read file which enforces workspace boundary confinement, and unlike run skill...

6.2CVSS6AI score0.00234EPSS
Exploits1References5
Snyk
Snyk
added 2026/04/08 10:12 p.m.4 views

Arbitrary Code Injection

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...

8.8CVSS6.2AI score0.00558EPSS
Exploits1References2
Snyk
Snyk
added 2026/04/08 9:52 p.m.1 views

Command Injection

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...

9.6CVSS6.2AI score0.00419EPSS
Exploits1References2
NVD
NVD
added 2026/04/08 9:17 p.m.2 views

CVE-2026-39890

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

9.8CVSS0.0058EPSS
Exploits0References1
NVD
NVD
added 2026/04/08 9:17 p.m.3 views

CVE-2026-39889

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U Agent-to-User event stream server in PraisonAI exposes all agent activity without authentication. The createa2uroutes function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe,...

7.5CVSS0.00425EPSS
Exploits0References1
NVD
NVD
added 2026/04/08 9:17 p.m.0 views

CVE-2026-39891

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

8.8CVSS0.00558EPSS
Exploits1References1
NVD
NVD
added 2026/04/08 9:17 p.m.0 views

CVE-2026-39888

PraisonAI is a multi-agent teams system. Prior to 1.5.115, executecode in praisonaiagents.tools.pythontools defaults to sandboxmode="sandbox", which runs user code in a subprocess wrapped with a restricted builtins dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess...

9.9CVSS0.00541EPSS
Exploits0References1
CVE
CVE
added 2026/04/08 8:46 p.m.6 views

CVE-2026-39891

PraisonAI’s multi-agent system contains a template injection in the create_agent_centric_tools() function prior to version 4.5.115. Tools such as acp_create_file process file content via template rendering, and user input from agent.start() could be rendered as template expressions instead of bei...

8.8CVSS5.9AI score0.00558EPSS
Exploits1References1Affected Software1
Cvelist
Cvelist
added 2026/04/08 8:46 p.m.20 views

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

8.8CVSS0.00558EPSS
Exploits1References1
Vulnrichment
Vulnrichment
added 2026/04/08 8:46 p.m.1 views

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

8.8CVSS5.9AI score0.00558EPSS
Exploits1References1
Cvelist
Cvelist
added 2026/04/08 8:45 p.m.16 views

CVE-2026-39890 PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

9.8CVSS0.0058EPSS
Exploits0References1
Rows per page
Query Builder