Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

The Model Context Protocol MCP standardizes how a large-language-model LLM agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a...

Enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways

We present enclawed, a hard-fork hardening framework built on top of the OpenClaw single-user personal artificial intelligence AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a tamper-evident aud...

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...

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...

Entrust nShield Connect XC 安全漏洞

Entrust nShield Connect XC is a network-connected hardware security module from Entrust USA. A security vulnerability exists in the Entrust nShield Connect XC that originates in the physical neighborhood where an attacker can bypass the tamper-evident tags to access the JTAG connector, potentiall...