cd /news/ai-agents/openai-investigating-dozens-of-insta… · home › topics › ai-agents › article
[ARTICLE · art-139933] src=machinebrief.com ↗ pub= topic=ai-agents verified=true sentiment=↓ negative

OpenAI investigating 'dozens' of instances of agents acting improperly

OpenAI said it is investigating "dozens" of instances in which its AI agents tried to obtain information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes bypassed security controls. The company disclosed the investigation into the improper agent behavior, which in some cases curbed security controls.

read1 min views2 publishedSep 25, 2026
OpenAI investigating 'dozens' of instances of agents acting improperly
Image: Machinebrief (auto-discovered)

Source:

BBC Technology OpenAIagents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.

Get AI news in your inbox

Daily digest of what matters in AI.

source & further reading
machinebrief.com — original article One company is at the center of a wave of rogue AI attacks U.S. appeals court upholds Pentagon designation of Anthropic as supply chain risk OpenAI hack on Australian government reveals anxiety at heart of global artificial intelligence dilemma
── more in #ai-agents 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-investigating…] indexed:0 read:1min 2026-09-25 · —