CVE-2026-45366 typescript-utcp: SSRF via attacker-controlled OpenAPI servers[0].url in HTTP communication protocol

typescript-utcp is a typescript implementation of UTCP. Prior to 1.1.2, the @utcp/http package is vulnerable to a blind Server-Side Request Forgery SSRF caused by a trust-boundary inconsistency between manual discovery and tool invocation. registerManual validates the discovery URL against an HTT...

Security, Privacy, and Ethical Risks in OpenClaw

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While OpenClaw shows strong potential for personal assistance,...

NPM: Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

NPM: Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret vulnerability discovered by ? in WordPress Npm network-ai versions = 5.4.4...

CVE-2026-45350

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chatcompletion API, t...

DNS Rebinding

MCP Java SDK is vulnerable to DNS Rebinding. The vulnerability is due to lack of Origin Validation, allowing a malicious website to bypass same-origin restrictions and access a local or network-private MCP server via the victim’s browser, enabling unauthorized tool invocation...

redhound-arsenal

Red Hound Arsenal Agent-consumable security skill library for...

OpenClaw: Gateway /tools/invoke tool escalation + ACP permission auto-approval

Summary OpenClaw Gateway exposes an authenticated HTTP endpoint POST /tools/invoke intended for invoking a constrained set of tools. Two issues could combine to significantly increase blast radius in misconfigured or exposed deployments: - The HTTP gateway layer did not deny high-risk session...

CVE-2026-25805

Zed Editor (multiplayer code editor) before version 0.219.4 fails to reveal the parameters used when invoking a tool and does not show post-invocation parameters, creating a potential for unnoticed use of unwanted or malicious values. A fix is included in 0.219.4 which adds expandable tool call d...

Zed 安全漏洞

Zed is a code editor developed by Zed Industries. Versions of Zed prior to 0.219.4 contained security vulnerabilities. These vulnerabilities stemmed from insufficient display of tool invocation parameters, allowing malicious values to be used without being detected by users...

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models LLMs are...

From runtime risk to real‑time defense: Securing AI agents

AI agents, whether developed in Microsoft Copilot Studio or on alternative platforms, are becoming a powerful means for organizations to create custom solutions designed to enhance productivity and automate organizational processes by seamlessly integrating with internal data and systems. From a...

EUVD-2025-28908

Malicious code in bioql PyPI...

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System

LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt TIP, which...

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Large Language Models LLMs still struggle with the structured reasoning and tool-assisted computation needed for problem solving in cybersecurity applications. In this work, we introduce "random-crypto", a cryptographic Capture-the-Flag CTF challenge generator framework that we use to fine-tune a...

Network Reconnaissance & Vulnerability Assessment Tool: ReconScan

Network Reconnaissance & Vulnerability Assessment Tool The project currently consists of two major components: a script invoking and aggregating the results of existing tools, and a second script for automated analysis of the aforementioned results from the perspective of exploitability. In terms...