Tool Calling in Spring AI 2.0: A Composable, Agentic Architecture

Tool calling — the ability for an AI model to invoke application-defined functions and act on the results — is the essential building block of agentic AI systems. A model that can discover information, take action, and loop until a goal is reached is an agent. Spring AI 2.0 rearchitects tool...

PT-2026-49187

Name of the Vulnerable Software and Affected Versions OttoKit versions prior to 1.1.28 Description Unauthenticated PHP Object Injection occurs in the software. PHP Object Injection is a vulnerability that allows an attacker to pass malicious serialized objects into the application, which can lead...

kiro-cybersecurity-skills

CyberSecurity Skills A collection of 15 security workflows co...

CVE-2026-50287 Missing Authentication for Critical Function in @agenticmail/mcp

AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCPHTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can...

CVE-2026-40677

The use of insecure HTTP transport within AMD optional tools could allow an attacker to conduct a man-in-the-middle attack, potentially leading to arbitrary code execution...

EUVD-2026-36488

The use of insecure HTTP transport within AMD optional tools could allow an attacker to conduct a man-in-the-middle attack, potentially leading to arbitrary code execution...

CVE-2026-40677

The vulnerability CVE-2026-40677 affects AMD optional tools that use insecure HTTP transport, enabling a potential attacker to perform a man-in-the-middle attack and potentially achieve arbitrary code execution. The issue stems from unencrypted transport within these tools, which could allow inte...

CVE-2026-40677

The use of insecure HTTP transport within AMD optional tools could allow an attacker to conduct a man-in-the-middle attack, potentially leading to arbitrary code execution...

CVE-2026-40677

The use of insecure HTTP transport within AMD optional tools could allow an attacker to conduct a man-in-the-middle attack, potentially leading to arbitrary code execution...

Exploit for CVE-2026-35273

🚨 CVE-2026-35273 - Oracle PeopleSoft PeopleTools Unauthenticat...

Vulnerability handling in Oracle PeopleSoft Enterprise PeopleTools

Oracle has identified a vulnerability in Oracle PeopleSoft Enterprise PeopleTools versions 8.61 and 8.62. This vulnerability allows unauthorized attackers to exploit the system via HTTP remotely. This can lead to remote code execution, which may result in the complete takeover of the system. The...

PT-2026-48888

Name of the Vulnerable Software and Affected Versions AMD optional tools affected versions not specified Description The use of insecure HTTP transport within the auto-updater allows for a man-in-the-middle attack, which is a technique where an attacker intercepts communication between two partie...

CVE-2026-53818

OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools...

CVE-2026-53814

OpenClaw before 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority instead of hook-appropriate scope. Attackers with a valid hook token can exploit the /hooks/agent endpoint to cause spawned CLI runtimes ...

Incorrect Privilege Assignment

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Privilege Assignment due to the incorrect assignment of owner-scoped MCP loopback authority to hook-triggered agent processes. An attacker can perform unauthorized privileged...

CVE-2026-12024

Insufficient policy enforcement in DevTools in Google Chrome prior to 149.0.7827.115 allowed a remote attacker to bypass same origin policy via a crafted HTML page. Chromium security severity: High...

CVE-2026-53818 OpenClaw < 2026.4.24 - Owner-Only Tool Policy Bypass via MCP Loopback

OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools...

CVE-2026-53818 OpenClaw < 2026.4.24 - Owner-Only Tool Policy Bypass via MCP Loopback

OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools...

CVE-2026-53818 OpenClaw < 2026.4.24 - Owner-Only Tool Policy Bypass via MCP Loopback

OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools...

CVE-2026-53818

OpenClaw CVE-2026-53818 affects OpenClaw prior to 2026.4.24. It describes an authorization bypass in the MCP loopback feature that lets non-owner callers skip owner-only tool policies and before-tool-call hooks, potentially causing invocation of owner-only behavior to execute restricted tools whe...