CVE-2026-110845

n8n before 1.123.83, 2.x before 2.41.4, and 2.42.x before 2.42.1 contains a code execution vulnerability in the Git node Log operation, which fails to strip a repository's local git configuration before invoking an external program. Authenticated members who can point the node, including as an...

@agent-tool-platform/agent-kit (>=0.2.0, <=0.4.0), @agent-tool-platform/ast-summarizer (>=0.1.0, <=0.1.1) +592 more potentially affected by CVE-2026-92081 via fastify (>=5.0.0-alpha.2, <=5.12.4)

fastify NPM version =5.0.0-alpha.2, =0.2.0, =0.1.0, =0.1.0, =0.1.0, =1.0.4, =0.4.0, =0.0.0-vBETA-20260417080530, =0.0.1, =1.60.2, =1.0.0, =0.0.0, =2.0.1, =2.0.5 and more Source cves: CVE-2026-92081 Source advisory: OSV:GHSA-4MH8-R7RC-XPVC...

@agent-tool-platform/agent-kit (>=0.2.0, <=0.4.0), @agent-tool-platform/ast-summarizer (>=0.1.0, <=0.1.1) +592 more potentially affected by CVE-2026-92081 via fastify (>=5.0.0-alpha.2, <=5.12.4)

fastify NPM version =5.0.0-alpha.2, =0.2.0, =0.1.0, =0.1.0, =0.1.0, =1.0.4, =0.4.0, =0.0.0-vBETA-20260417080530, =0.0.1, =1.60.2, =1.0.0, =0.0.0, =2.0.1, =2.0.5 and more Source cves: CVE-2026-92081 Source advisory: GHSA-4MH8-R7RC-XPVC...

@agent-tool-platform/agent-kit (>=0.2.0, <=0.4.0), @agent-tool-platform/ast-summarizer (>=0.1.0, <=0.1.1) +581 more potentially affected by CVE-2026-84504 via fastify (>=5.0.0-alpha.2, <=5.12.1)

fastify NPM version =5.0.0-alpha.2, =0.2.0, =0.1.0, =0.1.0, =0.1.0, =1.0.4, =0.0.0-vBETA-20260417080530, =0.0.1, =1.60.2, =1.0.0, =0.0.0, =2.0.1, =0.1.0, =0.2.7 and more Source cves: CVE-2026-84504 Source advisory: GHSA-667R-XXJV-C9MM...

Missing Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Missing Authorization via improper enforcement of sender allowlists in multi-person direct messages group DMs. A disallowed participant present in a Slack group DM can trigger an OpenClaw...

CVE-2026-86996

n8n is an open source workflow automation platform. Prior to 2.37.7 and 2.38.2, the workflow setting named This workflow can be called by was enforced by the Execute Workflow node but not when a workflow was attached to an Agent as a tool. A user able to build an Agent could invoke a restricted...

GHSA-7HGX-277F-7VMG n8n: Agent Workflow Tool Bypasses Sub-Workflow Caller Policy

Impact A workflow's "This workflow can be called by" setting was enforced by the Execute Workflow node but was not consulted when the same workflow was attached to an Agent as a tool. A user who could build an Agent could therefore call a workflow that its owner had restricted, and read back what...

Missing Authorization

Overview n8n is a n8n Workflow Automation Tool Affected versions of this package are vulnerable to Missing Authorization in the enforcement of workflow caller policies when a workflow is attached as an Agent tool. An attacker can access restricted workflow outputs by constructing an Agent that...

EUVD-2026-74267

n8n is an open source workflow automation platform. Prior to 2.37.7 and 2.38.2, the workflow setting named This workflow can be called by was enforced by the Execute Workflow node but not when a workflow was attached to an Agent as a tool. A user able to build an Agent could invoke a restricted...

PT-2026-88505

Name of the Vulnerable Software and Affected Versions n8n versions prior to 2.37.7 n8n versions prior to 2.38.2 Description An authorization bypass exists when a workflow is attached to an Agent as a tool. While the setting This workflow can be called by is enforced by the Execute Workflow node, ...

Langflow agent Function Bypass

The vulnerability of the getflowbyidorendpointname function in the Langflow agent and workflow creation/execution tools relates to bypassing authentication using a user-controlled key. Exploiting this vulnerability could allow an attacker to circumvent existing security restrictions using an...

Command Injection

Overview Affected versions of this package are vulnerable to Command Injection via the ExecTool.Execute function in the exec tool component. An attacker can execute arbitrary operating system commands by providing crafted input to this function. Remediation There is no fixed version for...

CVE-2026-53808

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

Malware in @uipath/agent-tool

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

Malicious code in @uipath/agent-tool (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 1bf0a4aecf9abab564a34cce85bbd0992c11840dfce74518bc3f21d5fc4e47ad Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2026-3526 Malicious code in @uipath/agent-tool (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 1bf0a4aecf9abab564a34cce85bbd0992c11840dfce74518bc3f21d5fc4e47ad Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

CVE-2026-45001 OpenClaw < 2026.4.20 - Gateway Config Mutation Guard Bypass via Agent Tool Access

OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.apply endpoints that fails to protect operator-trusted settings including sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

CVE-2026-45001 OpenClaw < 2026.4.20 - Gateway Config Mutation Guard Bypass via Agent Tool Access

OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.apply endpoints that fails to protect operator-trusted settings including sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

CVE-2026-45001

OpenClaw prior to 2026.4.20 contains a guard bypass in the agent-facing gateway config.patch and config.apply endpoints that can persist unauthorized changes to operator-trusted settings (sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, and...

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data exfiltration, can cause irreversible harm. Existing defenses are...