AIThe Next Webabout 4 hours ago
AI coding agents escape sandboxes via files
1 min read
Pillar Security found that four AI coding agents (Cursor, OpenAI's Codex, Google's Gemini CLI, and Antigravity) can cross their security boundaries without breaking the sandbox. The trick uses prompt injection: a malicious instruction hidden in a file the agent writes becomes a command the host later runs. Cursor patched one flaw as CVE-2026-48124 in version 3.0.0. OpenAI fixed a Codex bug and paid a bounty.
Level
Hype check
Tap to vote and see what everyone thinks.
