llm-technique

【开发与工程】Auth assessment of LLM apps, RAG pipelines and agent/MCP systems: prompt injection, jailbreak taxonomy, indirect channels, tool poisoning, excessive agency, system-prompt leakage, embedding attacks, unbounded consumption. Maps to OWASP LLM Top 10 v2 (2025).

独立 GitHub 快照 · 自动分类 · 以原作者文档为准