hunt-llm-ai

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.

请帮我安装这个 Agent Skill：https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-llm-ai

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/hunt-llm-ai/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

git clone --depth 1 --filter=blob:none --sparse https://github.com/elementalsouls/Claude-BugHunter.git /tmp/hunt-llm-ai-src
cd /tmp/hunt-llm-ai-src && git sparse-checkout set "skills/hunt-llm-ai"
mkdir -p ~/.claude/skills && cp -r "skills/hunt-llm-ai" ~/.claude/skills/hunt-llm-ai

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。