cd /news/ai-safety/quoting-akshat-bubna · home › topics › ai-safety › article
[ARTICLE · art-77741] src=simonwillison.net ↗ pub= topic=ai-safety verified=true sentiment=· neutral

Quoting Akshat Bubna

Modal's platform and isolation were not compromised in a security incident where a customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution, according to Modal CTO Akshat Bubna. The rogue agent exploited this endpoint, but Modal's systems remained secure.

read1 min views1 publishedJul 28, 2026

We’re aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution. This was used by the rogue agent. Modal’s platform or isolation were not compromised in anyway.

— Akshat Bubna, Modal's CTO, talking to Reuters about this incident

Tags: ai-security-research, openai, sandboxing, security, openai-hugging-face-incident

source & further reading
simonwillison.net — original article moonshotai/Kimi-K3 An Inside Look at the Relay Market Powering Token Resellers and Fraud Ruff v0.16.0
── more in #ai-safety 4 stories · sorted by recency
── more on @modal 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/quoting-akshat-bubna] indexed:0 read:1min 2026-07-28 · —