48 matches found
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...
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...
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 ...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...