BestHub
Sign in
Tagged articles
2 articles
Page 1 of 1
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Apr 30, 2026 · Artificial Intelligence

When Is Claude Code’s Memory Injected into system_prompt? Interview Insight

The article explains that Claude Code loads persisted memory once at REPL startup via _build_system(), inserts it as the 10th segment of system_prompt, enforces a 200‑line limit on MEMORY.md, deliberately avoids side‑effects in get_memory_dir(), and only refreshes the prompt with the /model command.

Claude CodeInterview preparationLLM
0 likes · 11 min read
When Is Claude Code’s Memory Injected into system_prompt? Interview Insight
SuanNi
SuanNi
Apr 10, 2026 · Information Security

How Tiny Memory Files Turn AI Assistants into Hackable Backdoors

Researchers from UC Berkeley, NUS, Tencent and ByteDance reveal that a single hidden line in an AI assistant’s memory file can trigger OpenClaw to leak core keys or erase disks, detailing a three‑dimensional CIK attack model, real‑world tests on four top LLMs, and mitigation strategies.

AI securityCIK architectureMemory injection
0 likes · 11 min read
How Tiny Memory Files Turn AI Assistants into Hackable Backdoors