Security boundaries in agentic architectures - Vercel

kept by eddie feb 25

Vercel recommends separating agent harness from generated code execution in isolated sandboxes with secret injection to prevent prompt injection and credential theft in agentic architectures.

$1 million hacker challenge for Vercel Sandbox - Vercel
Vercel launches a two‑week public HackerOne bounty offering up to $1 million for researchers who can escape its Sandbox microVM isolation.
also on Vercel Sandbox, Vercel, #security, #developer-tools
Designing AI agents to resist prompt injection
OpenAI argues that defending against prompt injection in AI agents requires treating attacks as social engineering and designing systems to constrain impact rather than just filtering inputs.
also on #prompt-injection, #security, #ai-agents
HackMyClaw | Hacker News
A prompt injection challenge testing whether an AI email assistant (Fiu) could be tricked into leaking secrets ended with no successful breaches.
also on #prompt-injection, #security, #ai-agents
5 Trends That Defined AI Engineering at World’s Fair 2026
AI engineering shifted from building with agents to building reliable systems around them, focusing on loop engineering, skills, and forward deployed engineers.
also on Vercel, Cursor, Claude Code, #ai-agents, #developer-tools
Why AI Swarms Cannot Build Architecture | An analysis of the structural limitations preventing AI agent swarms from producing coherent software architecture
AI agent swarms cannot produce coherent software architecture because architecture requires global invariants, temporal persistence, and enforcement authority—properties that swarms structurally lack.
also on #software-architecture, Cursor, #ai-agents