↓ Skip to main content

Rony Utevsky | Security Research & Exploit Write-ups

Rony Utevsky | Security Research & Exploit Write-ups

Close menu

Adversa AI

Cryptographic Context Injection: Zero-Confirmation Data Theft from Grok

Cryptographic Context Injection: Zero-Confirmation Data Theft from Grok

20 August 2026·4 mins

Security Research AI Security Cryptographic Context Injection Zero-Confirmation Data Exfiltration Prompt Injection LLM Grok XAI Agentic AI Adversa AI

DeepJack: a 1-click deeplink RCE in Cursor via a lying MCP-install dialog

DeepJack: a 1-click deeplink RCE in Cursor via a lying MCP-install dialog

15 July 2026·2 mins

Security Research AI Security DeepJack RCE MCP Cursor Deeplink Argument Injection Adversa AI

SymJack: the approval prompt is lying to you. A symlink-hijack RCE in five AI coding agents

SymJack: the approval prompt is lying to you. A symlink-hijack RCE in five AI coding agents

26 May 2026·2 mins

Security Research AI Security SymJack RCE Symlinks MCP Claude Code Cursor Antigravity Copilot Grok Codex Adversa AI

TrustFall: Coding Agent Security Flaw Enables One-Click RCE

TrustFall: Coding Agent Security Flaw Enables One-Click RCE

7 May 2026·2 mins

Security Research AI Security RCE MCP Claude Code Cursor Gemini CLI Copilot Adversa AI