Lucene search
+L

48 matches found

Vulnrichment
Vulnrichment
•added 2026/10/06 2:07 p.m.•18 views

CVE-2026-105789 Microsoft UFO: Arbitrary file write in the Linux MCP `execute_command` tool

Microsoft UFO is an open-source framework for intelligent automation across devices and platforms. Prior to 3.0.9, the executecommand tool in ufo/client/mcp/httpservers/linuxmcpserver.py treats sort and uniq as read-only commands while the free-form command parameter can select their file-output...

5.4CVSS6.6AI score0.007EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/10/06 2:07 p.m.•46 views

CVE-2026-105789 Microsoft UFO: Arbitrary file write in the Linux MCP `execute_command` tool

Microsoft UFO is an open-source framework for intelligent automation across devices and platforms. Prior to 3.0.9, the executecommand tool in ufo/client/mcp/httpservers/linuxmcpserver.py treats sort and uniq as read-only commands while the free-form command parameter can select their file-output...

5.4CVSS0.007EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/06 2:07 p.m.•34 views

CVE-2026-105789

The Microsoft UFO open-source automation framework is vulnerable to an arbitrary file write in the Linux MCP execute_command tool (specifically within ufo/client/mcp/http_servers/linux_mcp_server.py) prior to version 3.0.9 . The root cause is that while sort and uniq are treated as read-only, an ...

5.4CVSS6.6AI score0.007EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/10/06 12:00 a.m.•14 views

CVE-2026-105789: Improper Neutralization of Argument Delimiters in a Command

Microsoft UFO is an open-source framework for intelligent automation across devices and platforms. Prior to 3.0.9, the executecommand tool in ufo/client/mcp/httpservers/linuxmcpserver.py treats sort and uniq as read-only commands while the free-form command parameter can select their file-output...

5.4CVSS6.6AI score0.007EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/09/14 2:19 p.m.•62 views

CVE-2026-57125 PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agentyaml, and the approve field can mark executecommand as YAML-approved before @requireapproval checks critical tools. This...

9.8CVSS0.00601EPSS
SaveExploits0References3
NVD
NVD
•added 2026/09/14 3:16 a.m.•17 views

CVE-2026-90618

A flaw has been found in GH05TCREW PentestAgent up to cf882dabea3ed91cef016cdd115e5426315665a2. This issue affects the function LocalRuntime.executecommand of the file runtime/runtime.py of the component LocalRuntime. Executing a manipulation can lead to os command injection. The attack may be...

7.5CVSS0.02129EPSS
SaveExploits0References7
CVE
CVE
•added 2026/09/14 2:30 a.m.•53 views

CVE-2026-90618

GH05TCREW PentestAgent (up to commit cf882dabea3ed91cef016cdd115e5426315665a2) is vulnerable to OS command injection in the function LocalRuntime.execute_command within the file runtime/runtime.py. The flaw allows a remote, unauthenticated attacker with no user interaction to execute arbitrary co...

7.5CVSS6.9AI score0.02129EPSS
SaveExploits0References7
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/14 12:00 a.m.•6 views

CVE-2026-57125: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agentyaml, and the approve field can mark executecommand as YAML-approved before @requireapproval checks critical tools. This...

9.8CVSS6.2AI score0.00601EPSS
SaveExploits0References3
Snyk
Snyk
•added 2026/08/25 2:54 p.m.•12 views

Directory Traversal

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...

7.6CVSS6.1AI score0.00394EPSS
SaveExploits0References2
Mend
Mend
•added 2026/08/21 8:17 p.m.•21 views

CVE-2026-62316

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, ufo/client/mcp/httpservers/linuxmcpserver.py binds a FastMCP streamable HTTP server to localhost:8010 but does not validate the Host, Origin, or Sec-Fetch-Site headers. An...

8.8CVSS6.2AI score0.0051EPSS
SaveExploits0References5
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/21 12:00 a.m.•14 views

CVE-2026-62316: Exposure of Sensitive Information to an Unauthorized Actor

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, ufo/client/mcp/httpservers/linuxmcpserver.py binds a FastMCP streamable HTTP server to localhost:8010 but does not validate the Host, Origin, or Sec-Fetch-Site headers. An...

8.8CVSS6.2AI score0.0051EPSS
SaveExploits0References3
Mend
Mend
•added 2026/06/18 10:12 p.m.•10 views

CVE-2026-56074

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

6.8CVSS5.9AI score0.00176EPSS
SaveExploits0References7
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/18 12:00 a.m.•6 views

CVE-2026-56074: Incorrect Authorization

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

6.8CVSS5.9AI score0.00176EPSS
SaveExploits0References2
Mend
Mend
•added 2026/05/01 8:15 p.m.•42 views

CVE-2026-7593

A security vulnerability has been detected in Sunwood-ai-labs command-executor-mcp-server up to 0.1.0. This impacts the function executecommand of the file src/index.ts of the component MCP Interface. The manipulation leads to os command injection. Remote exploitation of the attack is possible. T...

7.5CVSS6.7AI score0.01498EPSS
SaveExploits0References7
CVE
CVE
•added 2026/05/01 8:15 p.m.•47 views

CVE-2026-7593

CVE-2026-7593 affects Sunwood-ai-labs command-executor-mcp-server up to 0.1.0. The vulnerability resides in the MCP Interface’s function execute_command (src/index.ts), enabling an attacker to perform OS command injection . Remote exploitation is possible, with public disclosures already availabl...

7.5CVSS6.7AI score0.01498EPSS
SaveExploits0References5
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/05/01 12:00 a.m.•10 views

CVE-2026-7593: Improper Neutralization of Special Elements used in an OS Command

A security vulnerability has been detected in Sunwood-ai-labs command-executor-mcp-server up to 0.1.0. This impacts the function executecommand of the file src/index.ts of the component MCP Interface. The manipulation leads to os command injection. Remote exploitation of the attack is possible. T...

7.5CVSS6.7AI score0.01498EPSS
SaveExploits0References3
Snyk
Snyk
•added 2026/04/10 7:28 p.m.•11 views

Incorrect Authorization

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Incorrect Authorization via the executecommand call. An attacker can access sensitive environment variables and exfiltrate confidential...

8.3CVSS5.9AI score0.00176EPSS
SaveExploits0References2
Snyk
Snyk
•added 2026/04/10 7:24 p.m.•16 views

Exposure of Sensitive Information Through Environmental Variables

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...

7.4CVSS6AI score0.00277EPSS
SaveExploits1References2
osv_ghsa
osv_ghsa
•added 2026/04/10 7:24 p.m.•23 views

GHSA-V8G7-9Q6V-P3X8 PraisonAIAgents: Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell Tool

Summary The executecommand function in shelltools.py calls os.path.expandvars on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False line 88 for security. This allows exfiltration of secrets stored in environment variabl...

7.4CVSS6.5AI score0.00277EPSS
SaveExploits1References3
Mend
Mend
•added 2026/04/09 9:27 p.m.•12 views

CVE-2026-40153

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the executecommand function in shelltools.py calls os.path.expandvars on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False line 88 for security. This...

8.3CVSS6AI score0.00277EPSS
SaveExploits1References5
Rows per page
Query Builder