Injection — AI skill for Claude Code
LLM 应用的 #1 安全风险——直接注入、间接注入、越狱、数据泄漏、工具滥用,以及多层防御策略.
How to install Injection
Installs to ~/.claude/skills/yibo365-agent-camp-injection/SKILL.md
mkdir -p ~/.claude/skills/yibo365-agent-camp-injection && curl -fsSL https://raw.githubusercontent.com/yibo365/agent-camp/HEAD/prompt/injection.md -o ~/.claude/skills/yibo365-agent-camp-injection/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Injection does
title: Prompt Injection 攻防 description: LLM 应用的 #1 安全风险——直接注入、间接注入、越狱、数据泄漏、工具滥用,以及多层防御策略。 pageClass: prompt-injection-page
Prompt 工程
Prompt Injection 攻防
LLM 应用的 #1 安全风险——直接注入、间接注入、越狱、数据泄漏、工具滥用,以及多层防御策略。
面试官想考什么
读完这篇你
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- Firecrawl MCP Server — 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c 6.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Godot AI
Native C++ AI assistant module for the Godot 4.7 editor - multi-provider LLM chat, GDScript code generation &
Nab
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin
LLM Diet
Cut AI coding tokens by 99%. Deterministic context injection for Claude Code, Cursor, Windsurf.
Agent Skills Deep Dive
A Python implementation of the Claude Agent Skills system — a sophisticated prompt-based meta-tool architectur
Prompt Architecture
Reference guide for designing production LLM prompt systems in this codebase. Covers the Two-Pass Gap Analysis
Secure AI Customer Support Platform
Secure LLM-powered customer support platform: an AI agent (Claude) with grounded RAG answers, authorization-en
Related Agents
LLM AI Hunter
LLM and Agentic AI vulnerability specialist. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI
Critic Security
Review code for OWASP-style security issues (injection, authn/authz, secrets, supply chain, LLM-specific) in p
Kavach LLM
KAVACH LLM/AI security specialist. Audits prompt injection (direct + indirect/RAG), jailbreak/persona/system-p