OpenACA is an open-source security scanner designed to audit AI agent stacks, including MCPs (Model Context Protocols), skills, and plugins. It helps developers identify vulnerabilities in the components that connect AI agents to tools and data sources, promoting safer agent deployments.
OpenACA is an open-source security scanner designed to audit AI agent stacks, including MCPs (Model Context Protocols), skills, and plugins. It helps developers identify vulnerabilities in the components that connect AI agents to tools and data sources, promoting safer agent deployments.
VulnFeed is an open-source MCP (Model Context Protocol) server that integrates nine security tools—such as Shodan, VirusTotal, and GreyNoise—into an AI agent, enabling automated vulnerability analysis via natural language queries and function calls.
Kinetk launches a multimodal intelligence API and Model Context Protocol (MCP) designed to ground AI agents by integrating various data types such as vision, audio, and text for more context-aware decision-making.
Trace Commons is an open repository designed to store and share code agent execution traces, aiming to improve transparency, reproducibility, and collaboration in AI-driven software engineering research.
This analysis was generated by AI and may contain inaccuracies. Always verify with original sources.
No related papers found.
A new open-source security scanner called OpenACA was released on June 16, 2026, targeting vulnerabilities in AI agent stacks including MCPs, skills, and plugins[^1]. The tool, shared via a "Show HN" post on the VulnFeed platform by Novadyne AI, aims to help developers identify security gaps in their agentic AI deployments. By scanning common integration points and plugin ecosystems, OpenACA addresses growing concerns around supply-chain risks and privilege escalation in AI agent architectures. The release signals a proactive shift in the AI security landscape as more organizations adopt agent-based workflows.
Omnigent is an open-source meta-harness designed to manage and orchestrate multiple AI agents from different providers in a unified interface, simplifying workflow automation and agent coordination.
OpenACA is an open-source security scanner designed to audit AI agent stacks, including MCPs (Model Context Protocols), skills, and plugins. It helps developers identify vulnerabilities in the components that connect AI agents to tools and data sources, promoting safer agent deployments.