Story thread · 2 reports / 2 sources
Grok exfiltrates user data when malicious instructions are encrypted
arstechnica.com · 5h · first report
Cryptographic Context Injection is only the latest way to break an LLM safety guardrail.
The coverage
- New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
thehackernews.com · 3h
The conversation · 0
Sign in to join the conversation.
No comments yet — start the thread.