Prompt Injection Attacks

Untrusted text that rewrites your instructions, and why filtering isn't enough.

2 articles

The prompt injection series

Listed inPrompt Injection Attacks Safety & EthicsonAug 15, 2026

Years of worked examples showing why filtering does not solve injection, and why the dual-LLM pattern is the closest thing to a fix.

External

Simon Willison · simonwillison.net

#security

#injection

Prompt Injection Attacks

Listed inPrompt Injection Attacks Safety & EthicsonSep 18, 2025

Untrusted text that rewrites your instructions, and why filtering isn't enough.

Advanced9 minDraft

#security