// GeminiHIGH
Researchers disclosed sandbox escape vulnerabilities in Gemini CLI and three other AI coding agents (Cursor, Codex, Antigravity). The escapes exploit a trust boundary where sandboxed agents can write files that are later read and executed by trusted tools outside the sandbox. Attackers can inject malicious instructions via prompts in documentation, dependencies, or diffs to achieve local command execution on the developer's machine.
- Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes(opens in a new tab)
- Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes(opens in a new tab)
- Researchers bypass sandbox security in Cursor, Codex, and Gemini(opens in a new tab)
- Cursor's Unpatched Zero-Day Lets a Fake git.exe Hijack Any Windo(opens in a new tab)
// Get alerts for Gemini