Tech
History poisoning turns coding agents into attackers
The case
Darktrace has published a demo that breaks an assumption most of us take for granted.
Claude Code, Codex and Kiro-CLI store the conversation history on disk without checking that those responses actually came from the model (Source: darktrace.com).
The agent reads that history on startup and treats it as trusted context, and I already see gaps in this...
Picture a malicious package installed on a developer's machine, and that package writes a fake conversation into the hist...
Read the full discussion on Dev.to
This article was aggregated from Dev.to. Click to join the conversation.
View on Dev.to