Lucene search
+L

48 matches found

NVD
NVD
•added 2026/10/23 1:17 p.m.•21 views

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...

7.8CVSS0.0024EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
•added 2026/10/23 12:07 p.m.•13 views

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...

7.8CVSS5.8AI score0.0024EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/10/23 12:07 p.m.•37 views

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...

7.8CVSS0.0024EPSS
SaveExploits0References1
EUVD
EUVD
•added 2026/10/23 12:07 p.m.•21 views

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...

7.8CVSS5.8AI score0.0024EPSS
SaveExploits0References1
CVE
CVE
•added 2026/10/23 12:07 p.m.•63 views

CVE-2026-57142

The PraisonAI multi-agent system (versions >= 4.5.87 and

7.8CVSS5.8AI score0.0024EPSS
SaveExploits0References1
osv_cve
osv_cve
•added 2026/10/23 11:58 a.m.•22 views

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,...

7.8CVSS5.8AI score
SaveExploits0References3
CNNVD
CNNVD
•added 2026/10/23 12:00 a.m.•17 views

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...

7.8CVSS6.9AI score0.0024EPSS
SaveExploits0References1
PyPA
PyPA
•added 2026/10/15 10:22 a.m.•21 views

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...

6.9CVSS6AI score0.00337EPSS
SaveExploits0References7Affected Software1
NVD
NVD
•added 2026/10/12 1:17 p.m.•28 views

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...

8.5CVSS0.00749EPSS
SaveExploits0References5
Vulnrichment
Vulnrichment
•added 2026/10/12 12:13 p.m.•17 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/10/12 12:13 p.m.•18 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References5
CVE
CVE
•added 2026/10/12 12:13 p.m.•33 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References5
Mend
Mend
•added 2026/10/12 12:13 p.m.•19 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References5
Cvelist
Cvelist
•added 2026/10/12 12:13 p.m.•45 views

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...

8.5CVSS0.00749EPSS
SaveExploits0References5
osv_cve
osv_cve
•added 2026/10/12 12:13 p.m.•36 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References7
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/10/12 12:00 a.m.•18 views

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...

8.5CVSS6AI score0.00749EPSS
SaveExploits0References2
NVD
NVD
•added 2026/10/06 2:17 p.m.•21 views

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...

5.4CVSS0.007EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/06 2:07 p.m.•37 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
SaveExploits0References6
EUVD
EUVD
•added 2026/10/06 2:07 p.m.•45 views

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...

5.4CVSS6.6AI score0.007EPSS
SaveExploits0References4
Mend
Mend
•added 2026/10/06 2:07 p.m.•15 views

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...

5.9CVSS6.6AI score0.007EPSS
SaveExploits0References6
Rows per page
Query Builder