Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Acronis

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 3

  1. Taiwan Investigates BossAI Emergency Dispatch System Breach

    Taiwan’s Ministry of Justice Investigation Bureau said it identified three suspects in the BossAI breach of central and local firefighting systems, with two detained by court order. Investigators said the suspects used AI agents as penetration tools from April 2026 and hosted the automated attack system on overseas VPS servers to steal OHCA dispatch data for sale to cooperating funeral businesses. Acronis separately claimed BossAI used 12 AI agents to target hundreds of organizations across 11 countries.

    iThome 台湾 · 🔥 0
  2. Acronis Details BossAI Multi-Agent Attack Architecture

    Acronis Threat Research Unit reported that BossAI targeted Taiwan’s emergency-service systems and organizations across 11 other countries, although the research does not show that every targeted organization was compromised. Researchers recovered more than 90,000 files totaling about 9 GB from a suspected misconfigured development environment and reconstructed an architecture integrating 12 AI agents, MCP-connected tools, Skills, and locally hosted models with safeguards removed. Acronis said only nine agents operated during the investigation, coordination remained manual, and the agents produced substantial false positives while failing to breach systems with effective authentication, workflow access controls, and endpoint filtering.

    iThome 台湾 · 🔥 0
  3. Acronis says BossAI targeted Taiwan emergency services

    Acronis disclosed that a Hualien-based actor built BossAI, a 12-agent system that targeted organizations across 11 countries over 12 days. Its agents coordinated reconnaissance, vulnerability scanning, attack-code writing and exploitation through MCP-connected tools including Nmap, sqlmap, Metasploit, Hydra and Ghidra. Acronis says modified DeepSeek, GLM and Qwen models performed much of the work, while Hermes led reconnaissance, weakness analysis and exploitation, and attackers accessed sensitive Taipei emergency-care and 119 dispatch records.

    iThome 台湾 · 🔥 0

Experience and discussion from the community

Share my Acronis experienceAsk about Acronis

Nobody has shared their experience with Acronis yet.