---
schema_version: '1.0'
id: news-20260910-b0a273
title: Protecting against indirect prompt injection attacks in MCP - Microsoft for
  Developers
url: https://developer.microsoft.com/blog/protecting-against-indirect-injection-attacks-mcp/
url_hash: b0a273368a2c8e5a53848b8da2795e209410168dafc74cacf5c6e64ab8acc8ed
canonical_url: https://developer.microsoft.com/blog/protecting-against-indirect-injection-attacks-mcp
source: developer.microsoft.com
category: news/tech
category_raw: it_ai
region: null
tags:
- it
- it_ai
- claude
- web-research
lang: null
published_at: '2025-04-28T18:00:22Z'
fetched_at: '2026-09-10T16:31:18.453043Z'
updated_at: '2026-09-10T16:33:18Z'
status: published
content_hash: null
content_changed_at: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
summary_omitted_reason: license_restricted
redistribution: false
keywords_en:
- against
- artificial intelligence
- attacks
- Claude
- Developers
- for
- indirect
- injection
- it
- it_ai
- MCP
- Microsoft
- prompt
- Protecting
- technology
- web-research
entities_en:
- name: Claude
  type: artifact
topics_en:
- artificial intelligence
- technology
numeric_facts: []
entities:
- name: Claude
  type: artifact
key_facts: []
related: []
related_auto:
- name: AI
  type: concept
  weight: 1.0
- name: 医療診断
  type: concept
  weight: 1.0
- name: 大規模言語モデル
  type: concept
  weight: 1.0
computed_at: '2026-09-10T16:33:15Z'
---

# Protecting against indirect prompt injection attacks in MCP - Microsoft for Developers

## 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
- it / it_ai / claude / web-research

## Details
(本文なし。リンク先参照)

## Source
元記事: [Protecting against indirect prompt injection attacks in MCP - Microsoft for Developers](https://developer.microsoft.com/blog/protecting-against-indirect-injection-attacks-mcp/) — published 2025-04-28T18:00:22Z