---
title: "Anthropic Opus 5: The Most Prompt-Injection-Resistant Model Yet"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/25/boris-cherny/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_2075c06488d8485979929717"
published: "2026-07-25T00:42:59.000Z"
score: 76
channel: "ai"
tags: ["AI Security","Anthropic","Opus 5","Prompt Injection Defense"]
---

# Anthropic Opus 5: The Most Prompt-Injection-Resistant Model Yet

## AI commentary

> This brief message hits the most stubborn problem in AI application safety. If you're building user-facing systems with LLMs, Opus 5's injection defense improvement could mean fewer late-night security patches. Worth watching for follow-up benchmark disclosures.

## At a glance

According to Boris Cherny, Anthropic's latest Opus 5 model has achieved a significant breakthrough in prompt injection defense, making it the least injection-prone model from the team so far. Although specific evaluation scores have not been released, this progress is crucial for developers building secure applications with large language models, marking a key step forward in AI safety.

## Key points

- Opus 5 is Anthropic's most prompt-injection-resistant model to date.
- This information was revealed by Boris Cherny in a quote on Simon Willison's blog.
- Prompt injection is one of the top security challenges for LLM applications; this improvement directly reduces attack risks.
- Specific evaluation scores are 'buried' (not publicly disclosed), but the qualitative conclusion is clear.

## Full text

More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried …

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_2075c06488d8485979929717