48 matches found
CVE-2026-57142
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in...
CVE-2026-57142 PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in...
CVE-2026-57142 PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in...
EUVD-2026-108896
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in...
CVE-2026-57142
The PraisonAI multi-agent system (versions >= 4.5.87 and
CVE-2026-56838 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...
Mervin Praison PraisonAI command injection vulnerability
Versions Mervin Praison PraisonAI from 4.5.87 through 4.6.61 contain a security vulnerability. This vulnerability arises because the recipe’s execution strategy for dangerous tools only checks the requires.tools field in TEMPLATE.yaml; it fails to validate the agent-level tools declarations and...
PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments
SummaryPraisonAI gates dangerous tools file writes, deletes, shell/code execution behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments. Root...
CVE-2026-108953
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-108953 mac-shell-mcp before 2.0.0 OS Command Injection via execute_command Arguments
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
EUVD-2026-97360
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-108953
The software mac-shell-mcp before version 2.0.0 is vulnerable to an OS command injection (CWE-78) within the execute_command arguments. This flaw allows MCP clients to bypass the command whitelist by injecting shell metacharacters (e.g., ;) into arguments of safe commands like pwd. Successful exp...
CVE-2026-108953
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-108953 mac-shell-mcp before 2.0.0 OS Command Injection via execute_command Arguments
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-108953 mac-shell-mcp before 2.0.0 OS Command Injection via execute_command Arguments
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-108953: Improper Neutralization of Special Elements used in an OS Command
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into executecommand arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run...
CVE-2026-105789
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...
EUVD-2026-93406
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 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...