Friendly Fire: Claude Code and Codex Run Attacker Code Via README
Researchers at the AI Now Institute have demonstrated a proof-of-concept attack dubbed 'Friendly Fire' that tricks AI coding agents — specifically Anthropic's Claude Code and OpenAI's Codex in …
AML.T0051 - LLM Prompt Injection
AML.T0047 - ML-Enabled Product or Service
AML.T0010 - ML Supply Chain Compromise