cd /news/ai-safety/google-finds-ai-agent-writing-and-la… · home › topics › ai-safety › article
[ARTICLE · art-171104] src=helpnetsecurity.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Google finds AI agent writing and launching exploits with no human in the loop

Google Threat Intelligence Group and Mandiant reported that threat actors have begun letting AI agents carry out entire stages of live intrusions, with at least one operation converting a newly released patch into a working exploit without a human in the loop. The groups said the mechanics of the intrusions are unchanged — compromised credentials and unpatched systems remain the vectors — but the speed and scale at which frameworks can exploit them has increased.

by read1 min views2 publishedNov 17, 2026

Threat actors have started letting AI agents carry out whole stages of live intrusions, and at least one operation no longer needs a human to turn a newly released patch into a working attack, Google Threat Intelligence Group (GTIG) and Mandiant revealed. LLM maturity timeline (Source: Google) “While the mechanics of the intrusions remain the same, such as using compromised credentials and targeting unpatched systems, the speed and scale at which frameworks can exploit these … More

The post Google finds AI agent writing and launching exploits with no human in the loop appeared first on Help Net Security.

── more in #ai-safety 4 stories · sorted by recency
── more on @google threat intelligence group 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/google-finds-ai-agen…] indexed:0 read:1min 2026-11-17 · —