RAG Retriever V3

企业级文档检索系统，支持多模型语义嵌入、混合向量+关键词搜索、Cross-Encoder重排序与完整来源引用。

This skill appears to implement the advertised RAG functionality and is internally consistent. Before installing, consider: (1) OPENAI_API_KEY is used optionally but not listed as a required env var — only provide it if you want cloud embeddings. (2) The skill stores data and config locally (.rag3-config.json and a LanceDB data folder) — run it in a directory you control and inspect created files. (3) Xenova/transformers or other runtime libs may download model weights at runtime and can be resource‑heavy; if you have bandwidth or disk limits, test in a sandbox. (4) The RAG prompt generator accepts/embeds a systemPrompt; avoid adding untrusted documents to the corpus or passing arbitrary system prompts, because they can influence LLM outputs (prompt‑injection risk). (5) As with any third‑party code, review dependencies (package-lock.json) and run tests in an isolated environment before giving it access to sensitive data or credentials.

Type: OpenClaw Skill Name: rag-retriever-v3 Version: 3.0.0 The rag-retriever-v3 skill bundle is a legitimate and well-structured implementation of a Retrieval-Augmented Generation (RAG) system. It includes features for semantic embeddings (local via Transformers.js or remote via OpenAI), hybrid search (BM25 + Vector), RRF fusion, and Cross-Encoder reranking. Analysis of the source code (e.g., src/core/RAGRetrieverV3.js, src/cli.js) and documentation (SKILL.md) reveals no evidence of data exfiltration, malicious execution, persistence mechanisms, or harmful prompt injection. Dependencies such as @lancedb/lancedb and @xenova/transformers are appropriate for the stated purpose.