cyberivy

Search results for “AI Agents”

Full-text search across every article: title, summary, plain-language explanation, and the complete text — archived stories included. Typos are fine.

430 results for “AI Agents”

  1. AgentFootprint exposes the blind spot of AI agents

    #AgentFootprint#AI Agents#LLM Evaluation

    … Metric for LLM Agent Evaluation argues that LLM agents should not be evaluated only by accuracy, cost, and reliability. The researchers also measure what remains on disk after an agent run: logs, context snapshots, …

  2. Microsoft Agent Governance Toolkit: guardrails for AI agents

    #Microsoft#Agent Governance Toolkit#AI Security

    … open-source toolkit for runtime governance of autonomous AI agents. Microsoft describes the project as an MIT-licensed monorepo with packages for policy enforcement, identity, sandboxing and reliability engineering. The …

  3. SafeKeep shows why tool schemas make AI agents less safe

    #SafeKeep#AI Agent Security#Prompt Injection

    … Matter, examines an uncomfortable detail of modern AI agents: the risk is not only in the model's capabilities, but also in the way external tools are described inside the prompt. The authors show that schema-formatted …

  4. goose brings AI agents locally to desktop and terminal

    #goose#Block#Agentic AI Foundation

    What this is about goose is an open AI agent for your own computer. The tool originally came from Block's open-source program and is now part of the Agentic AI Foundation. It is available as a desktop app, CLI, and API, …

  5. Browser Use lets AI agents perform real web tasks

    #Browser Use#Browser Automation#AI Agents

    … It is a concrete tool in the browser automation for AI agents category. Its value is that teams can use it to make one recurring job around AI applications more tangible: give AI agents a reproducible interface to the …

  6. Hermes attack shows the risk of unattended AI agents

    #Hermes Agent#AI Security#AI Agents

    … of Thailand's Ministry of Finance in which an open Hermes AI agent ran unattended. According to Hunt.io, an exposed server held 585 files totaling roughly 470 MB: exploit code, web shells, credentials, scripts, tunneling …

  7. MCP Toolbox makes databases controllable for AI agents

    #MCP Toolbox#Google#Developer Tools

    … for Databases is an open-source Google tool that connects AI agents to databases through the Model Context Protocol standard. The practical reason for this tool check is version 1.7.0 from July 16, 2026: the release adds …

  8. BrowserOS lets AI agents work inside their own browser

    #BrowserOS#BrowserClaw#Browser Automation

    … is about BrowserOS is an open-source browser that treats AI agents as part of the browsing workflow rather than as a separate cloud service. The product page describes it as a privacy-first Chrome alternative with …

  9. Hundreds of AI agents accelerate attack on 395 organizations

    #PaperCut#AI Security#AI Agents

    … A suspected Russian-speaking attacker used hundreds of AI agents to exploit two vulnerabilities in PaperCut NG/MF. GreyNoise documented at least 440 compromised instances belonging to 395 organizations in 48 countries on …

  10. Geiger inventories AI agents and their access rights

    #Geiger#AI Agent Security#MCP Security

    What this is about People who test several coding agents, IDE extensions, and MCP servers can quickly lose track of what is installed. Geiger is an open-source command-line tool from Atomburst designed to make this local …

Browse all AI news in the archive