Lone operator uses 12 AI agents to breach Taiwanese emergency services and steal data
AI SECURITYAcronisredteam/daily · 1 source
- Severity
- High
- Sources
- 1
What happened
Acronis Threat Research Unit attributes BOSSAI, a 12-agent AI mesh linked to one operator in Hualien City, Taiwan, to attacks on organisations in 11 countries. Agents used MCP-connected tools including HexStrike AI and HalberdStrike, and commercial models refused until the operator switched to abliterated local models, which produced false positives. Defenders should patch exposed databases, remove default credentials, close legacy ports and enforce authentication on all APIs, and check for the indicators Acronis published. No CVE identifiers are given in the article.
For security analysts · Written by AI from 1 source · Wrong?
What to do
- Patch exposed databases and remove default credentials.
- Close old open ports that are no longer needed.
- Put login checks in front of every API, including those that serve dispatch and medical data.
- Check your environment for the indicators of compromise that Acronis published.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Cyber Security News
Who and what is in it
Companies