ai-prompt-injection

【数据与研究】Test LLM-backed apps for prompt injection (direct + indirect) and its consequences: data exfil, tool/function abuse, guardrail bypass. Load when the target is a chatbot/assistant/ agent, summarizes untrusted content, has tools/functions, or does RAG. Signals: "ask AI", system prompts, function-calling, "summarize this URL/file", agentic actions.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准