20945 matches found
EUVD-2026-10371
ImageMagick has Integer Overflow leading to out of bounds write in SIXEL decoder...
CVE-2026-4040 OpenClaw File Existence tools.exec.safeBins information exposure
A vulnerability was identified in OpenClaw up to 2026.2.17. This issue affects the function tools.exec.safeBins of the component File Existence Handler. The manipulation leads to information exposure through discrepancy. The attack needs to be performed locally. Upgrading to version...
EUVD-2026-11534
A security flaw has been discovered in CesiumGS CesiumJS up to 1.137.0. Affected by this issue is some unknown functionality of the file Apps/Sandcastle/standalone.html. The manipulation of the argument c results in cross site scripting. The attack can be launched remotely. The exploit has been...
Malicious Package
Overview svg-safety-tool is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...
Malicious code in svg-safety-tool (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 423523b3df147eccef394a43e71101674f003918fb09ae7121dac4c4ac474eff The package svg-safety-tool was found to contain malicious code. Source: ghsa-malware f31f6cc0f000af3b9a7f76332b14e7d9c33b2d0f80056695850c21490d0e41c...
MAL-2026-1364 Malicious code in svg-safety-tool (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 423523b3df147eccef394a43e71101674f003918fb09ae7121dac4c4ac474eff The package svg-safety-tool was found to contain malicious code. Source: ghsa-malware f31f6cc0f000af3b9a7f76332b14e7d9c33b2d0f80056695850c21490d0e41c...
EUVD-2026-11486
A weakness has been identified in OpenAkita up to 1.24.3. This impacts the function run of the file src/openakita/tools/shell.py of the component Chat API Endpoint. Executing a manipulation of the argument Message can lead to os command injection. The attack is restricted to local execution. The...
nah Claude Code Tool
Claude Code's permission system is allow-or-deny per tool, but that doesn't really scale. Deleting some files is fine sometimes. And git checkout is sometimes catastrophic. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool’s errand. What's...
Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection
Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...
ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool, enabling exploitable source-to-sink dataflows that only...
PT-2026-25015
Hyperterse is a tool-first MCP framework for building AI-ready backend surfaces from declarative config. Prior to v2.2.0, the search tool allows LLMs to search for tools using natural language. While returning results, Hyperterse also returned the raw SQL queries, exposing statements which were...
TinaCMS 安全漏洞
TinaCMS is an open-source headless CMS for Markdown, MDX, and JSON developed by Tina. Versions of TinaCMS prior to 2.1.8 contained a security vulnerability. This vulnerability stemmed from the TinaCMS CLI development server’s configuration using Vite, which disabled the built-in file system acces...
OpenClaw PRISM: A Zero-Fork, Defense-In-Depth Runtime Security Layer for Tool-Augmented LLM Agents
Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer...
AEGIS: No Tool Call Left Unchecked -- a Pre-Execution Firewall and Audit Layer for AI Agents
AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer with no framework-agnostic control point in between...
PT-2026-24945
A vulnerability was identified in OpenClaw up to 2026.2.17. This issue affects the function tools.exec.safeBins of the component File Existence Handler. The manipulation leads to information exposure through discrepancy. The attack needs to be performed locally. Upgrading to version...
CVE-2026-3959
A vulnerability was found in 0xKoda WireMCP up to 7f45f8b2b4adeb76be8c6227eefb38533fdd6b1e. Impacted is the function server.tool of the file index.js of the component Tshark CLI Command Handler. The manipulation results in os command injection. The attack needs to be approached locally. The explo...
CVE-2026-3959
The CVE concerns 0xKoda WireMCP (up to commit 7f45f8b2b4adeb76be8c6227eefb38533fdd6b1e). Affected is the function server.tool in index.js of Tshark CLI Command Handler, where input manipulation leads to OS command injection. Attack requires local access; public exploit exists. Product uses a roll...
CVE-2026-3959 0xKoda WireMCP Tshark CLI index.js server.tool os command injection
A vulnerability was found in 0xKoda WireMCP up to 7f45f8b2b4adeb76be8c6227eefb38533fdd6b1e. Impacted is the function server.tool of the file index.js of the component Tshark CLI Command Handler. The manipulation results in os command injection. The attack needs to be approached locally. The explo...
CVE-2026-3959
A vulnerability was found in 0xKoda WireMCP up to 7f45f8b2b4adeb76be8c6227eefb38533fdd6b1e. Impacted is the function server.tool of the file index.js of the component Tshark CLI Command Handler. The manipulation results in os command injection. The attack needs to be approached locally. The explo...
CVE-2026-3959 0xKoda WireMCP Tshark CLI index.js server.tool os command injection
A vulnerability was found in 0xKoda WireMCP up to 7f45f8b2b4adeb76be8c6227eefb38533fdd6b1e. Impacted is the function server.tool of the file index.js of the component Tshark CLI Command Handler. The manipulation results in os command injection. The attack needs to be approached locally. The explo...