Mandiant report says attackers now use agentic AI, with exploitation still the main way in
AI SECURITYGoogle Threat Intelligence Groupredteam/daily · 1 source
- Severity
- High
- Sources
- 1
What happened
A report from Mandiant and Google Threat Intelligence Group says criminals are using AI to speed up their attacks. Most attacks still get in through known weaknesses that were left unfixed, and the time defenders have to fix them is shrinking.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- Review long-lived CI/CD credentials, since one healthcare intrusion began with a single such credential.
- Restrict over-permissioned AI agents and check for unsigned plugins and MCP servers.
- Check whether the NVIDIA Container Toolkit, MCP server and Docker Model Runner flaws apply to your environment, noting that Docker Model Runner exploitability depends on runtime flags.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Qualys Threat Research