hunt-llm-ai
聚焦可证明的跨信任边界漏洞，减少误报与冗余
含诱导与注入攻击技术，可能被滥用或用于对抗模型
发现并验证 LLM/AI 功能中的安全缺陷，如提示注入与工具滥用
找 LLM/AI 系统里的安全问题：提示注入、通过工具或 markdown 偷跑数据、ASCII/Unicode 隐写等实战向缺陷。用于审计聊天机器人、RAG、agentic copilot 等能接外部输入或执行工具的系统。侧重可复现、能证明越过信任边界的漏洞并参考 OWASP 类别。
▸ 展开 SKILL.md 英文原文
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 s
帮我安装这个 skill：https://raw.githubusercontent.com/elementalsouls/Claude-BugHunter/main/skills/hunt-llm-ai/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/elementalsouls/Claude-BugHunter/main/skills/hunt-llm-ai/SKILL.md"## 11. LLM / AI FEATURES LLM bugs are only worth reporting when they cross a trust boundary you can **prove** — an OOB callback, a verbatim-reproducible secret, a cross-tenant record, or code execution. A model "saying something bad once" is confabulation, not a vulnerability. Read the False-Positive Gate before claiming anything. > **Naming note (was wrong in v1):** the model-level list is **OWASP Top 10 for LLM Applications 2025** (LLM01 Prompt Injection, LLM07 System Prompt Leakage, LLM08 Vector/Embedding Weaknesses). The agent-level list is **OWASP Top 10 for Agentic Applications (2026)** from the **Agentic Security Initiative (ASI)**, codes ASI01–ASI10. Do not write "OWASP ASI 2026" a