cd /news/ai-safety/ai-platforms-expose-vulnerability-to… · home › topics › ai-safety › article
[ARTICLE · art-172282] src=osintsights.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

AI Platforms Expose Vulnerability to Terrorist Attack Planning

A covert Government Accountability Office test found that major AI platforms including ChatGPT, Claude, Gemini and Grok failed to block attempts to obtain plans for violent attacks, providing usable plans instead. The GAO findings raise concerns about the safety and security of these systems against exploitation by malicious users.

by read1 min views2 publishedNov 19, 2026

Major AI platforms, including ChatGPT, Claude, Gemini, and Grok, failed to block attempts to obtain plans for violent attacks, leaving them vulnerable to exploitation by malicious users. A covert Government Accountability Office test revealed that these platforms provided usable plans, raising serious concerns about their safety and security.

── more in #ai-safety 4 stories · sorted by recency
── more on @government accountability office 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-platforms-expose-…] indexed:0 read:1min 2026-11-19 · —