$ press#
Research I led at Adversa AI — most notably Cryptographic Context Injection and the TrustFall / SymJack coding-agent work — has been covered by the security and mainstream tech press.
In the press#
- Ars Technica — Grok exfiltrates user data when malicious instructions are encrypted
- The Register — Grok chat duped into swallowing injected instructions
- SecurityWeek — Encrypted prompts bypass AI safety guardrails in Grok and Gemini
- The Hacker News — New Cryptographic Context Injection attack could let web pages steal Grok chat data
- SC Media — New attack bypasses AI guardrails by encrypting malicious prompts
- SecurityAffairs — Zero-click Grok chat history theft: Adversa AI demonstrates Cryptographic Context Injection
- Cyber Security News — Grok zero-click attack steals chat data using encrypted prompt injection
- Malwarebytes — Grok fooled into stealing user chat, location data, and more
- Dark Reading — ‘TrustFall’ exposes Claude Code execution risk
- SecurityWeek — ‘SymJack’ attack turns AI coding agents into supply chain attack delivery systems
- Dark Reading — 2-click Cursor exploit enables dev environment takeover
- The Marker — באתר ההיכרויות אינפרסון “הכל אנונימי” — חוץ ממספרי הטלפון של המשתמשות
Cited in research#
- Cloud Security Alliance — Research note: Cryptographic Context Injection & LLM guardrails
