@agent-tool-platform/agent-kit (>=0.2.0, <=0.4.0), @agent-tool-platform/ast-summarizer (>=0.1.0, <=0.1.1) +589 more potentially affected by CVE-2026-84504 via fastify (>=5.0.0, <=5.12.1)

fastify NPM version =5.0.0, =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: OSV:GHSA-667R-XXJV-C9MM...

@agent-tool-platform/agent-kit (>=0.2.0, <=0.4.0), @agent-tool-platform/ast-summarizer (>=0.1.0, <=0.1.1) +600 more potentially affected by CVE-2026-92081 via fastify (>=5.0.0, <=5.12.4)

fastify NPM version =5.0.0, =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: SNYK:JS-FASTIFY-19883909...

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...

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, ...

The vulnerability of the `get_flow_by_id_or_endpoint_name` function in the Langflow agent and workflow creation/execution tool allows a attacker to circumvent existing security restrictions.

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...

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 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...

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...

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...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

EUVD-2026-20639

PraisonAI has Template Injection in Agent Tool Definitions...

PraisonAI has Template Injection in Agent Tool Definitions

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user inpu...

Zed 后置链接漏洞

Zed is a code editor developed by Zed Industries. Versions of Zed prior to 0.225.9 contained a post-link vulnerability. This vulnerability stemmed from symbolic link escapes in the Agent file tool, which could lead to the exposure of sensitive data...

CVE-2026-22687

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, after WeKnora enables the Agent service, it allows users to call the database query tool. Due to insufficient backend validation, an attacker can use prompt‑based bypass...