AIシステムへのプロンプトインジェクション攻撃を防ぎ、入力検証とコンテキスト分離の設計指針を提供するスキル。 Anchors: • OWASP LLM Top 10 / 適用: LLMセキュリティ脅威モデリング / 目的: インジェクション攻撃の分類と防御パターン理解 • Simon Willison's Prompt Injection Research / 適用: 実攻撃パターン分析 / 目的: 実世界の攻撃事例から防御戦略を導出 • Defense in Depth principle / 適用: 多層防御設計 / 目的: 単一障害点の排除 Trigger: Use when designing prompt injection defenses, implementing AI security measures, sanitizing user inputs for LLM systems, separating trusted and untrusted contexts, conducting security reviews for LLM applications, mitigating indirect prompt injection risks.
Key Features
- Comprehensive skill evaluation and performance tracking
- Community-driven ratings and reviews
- Easy integration with Claude Code
- Regular updates and maintenance
Quick Start
TopRank Skills install daishiman/prompt-injection-defense
chat Comments (0)
Sign in to join the discussion and leave a comment.
Skill Details
GitHub Stars
5
GitHub Forks
0
Created
Jan 2026
Last Updated
8 months ago
tools
tools llm ai
Related Skills
Build your own?
Join 12,000+ developers contributing to the Claude ecosystem.
No comments yet. Be the first to share your thoughts!