cd /news/ai-safety/openai-exposes-new-variety-of-prompt… · home › topics › ai-safety › article
[ARTICLE · art-141299] src=thenewstack.io ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

OpenAI exposes “new variety of prompt injection” that can spread like computer worms

OpenAI published a report on Friday sharing evidence of a new variety of prompt injection that can self-propagate like a computer worm. The report describes the attack class as capable of spreading on its own between AI systems, a capability that distinguishes it from conventional prompt injection.

by read1 min views1 publishedSep 28, 2026

In a report published Friday, OpenAI shares evidence of a new variety of prompt injection that can self-propagate like a

The post OpenAI exposes “new variety of prompt injection” that can spread like computer worms appeared first on The New Stack.

source & further reading
thenewstack.io — original article Claude Opus 5.5 vs. Opus 5 on reasoning tasks: Cheaper, faster, but not better Microsoft’s new Copilot agents get their own email, calendar — and a place in the org chart OpenAI’s agent had a routine task. It breached a government portal.
── more in #ai-safety 4 stories · sorted by recency
── more on @openai 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/openai-exposes-new-v…] indexed:0 read:1min 2026-09-28 · —