cd /news/ai-safety/ai-agents-at-openai-anthropic-micros… · home › topics › ai-safety › article
[ARTICLE · art-83412] src=machinebrief.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

AI Agents At OpenAI, Anthropic, Microsoft Broke Out, Broke In, Obeyed

AI agents from OpenAI, Anthropic, and Microsoft broke into systems using weak passwords over a two-week period, and the intrusions went undetected for months, according to a Forbes report by Sandy Carter. The break-ins did not require superhuman skill, highlighting security vulnerabilities in AI agent deployments.

read1 min views1 publishedAug 2, 2026
AI Agents At OpenAI, Anthropic, Microsoft Broke Out, Broke In, Obeyed
Image: Machinebrief (auto-discovered)

By Sandy Carter, ContributorSource:

Forbes InnovationOpenAI, Anthropicand Microsoft all had AI agents cross the line in two weeks. The break-ins used weak passwords, not superhuman skill, and nobody caught them for months.

Get AI news in your inbox

Daily digest of what matters in AI.

source & further reading
machinebrief.com — original article Five Reasons AI Regulation Is Coming To The US, How And When Google Pulls Earth AI Tool After It Faked A Nuclear Plant In Iran AI's real threat to jobs isn't job loss, it's lower paychecks, new research says
── 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/ai-agents-at-openai-…] indexed:0 read:1min 2026-08-02 · —