---
schema_version: '1.0'
id: news-20260718-3a8691
url: https://www.wired.com/story/prompt-injection-attacks-are-thwarting-ai-hacking-agents/
url_hash: 3a86917801b9bd0a30c6b94fe680cb42c27769f2fd02608a9b1bffe00413569e
canonical_url: https://www.wired.com/story/prompt-injection-attacks-are-thwarting-ai-hacking-agents
source: wired
category: news/tech
category_raw: tech
region: usa
tags:
- アメリカ
- ニュース
lang: en
published_at: '2026-07-18T09:00:00Z'
fetched_at: '2026-07-18T16:12:27Z'
updated_at: '2026-07-18T16:14:55Z'
status: published
content_hash: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
entities:
- name: アメリカ
  type: location
- name: ニュース
  type: content
- name: Prompt
  type: technology
- name: Russian missile and drone attacks
  type: event
- name: Parents
  type: person
- name: reward_hacking
  type: event
- name: Agents
  type: concept
key_facts: []
related: []
related_auto:
- name: WTA
  type: organization
  weight: 1.0
- name: FIFAワールドカップ2026
  type: event
  weight: 1.0
- name: Location
  type: UNKNOWN
  weight: 1.0
- name: Mastodon
  type: platform
  weight: 1.0
- name: FIFAワールドカップ
  type: event
  weight: 1.0
title: Prompt Injection Attacks Are Thwarting AI Hacking Agents
---

# Prompt Injection Attacks Are Thwarting AI Hacking Agents

## TL;DR
（要約なし・原文はリンク先を参照 / No summary available; see the source link.）

## Key Points
- アメリカ / ニュース

## Details
(本文なし。リンク先参照)

## Source
元記事: [Prompt Injection Attacks Are Thwarting AI Hacking Agents](https://www.wired.com/story/prompt-injection-attacks-are-thwarting-ai-hacking-agents/) — published 2026-07-18T09:00:00Z