semantic-search

企业级语义检索技能，支持表格/字段/文件搜索和 Text-to-SQL 数据生成

This package appears to implement the advertised semantic-search functionality, but review carefully before installing: - Expect to provide FlightSQL credentials; the skill will connect to your DB and run queries (Text-to-SQL may execute SELECTs). Provide a least-privilege DB account and limit network access. - The code attempts to import project-level configs (utils.config) by adding parent paths to sys.path. That means the skill can pick up and use configuration files or credentials present in the surrounding environment — run it in an isolated container / sandbox to avoid accidental use of host secrets. - The docs reference many optional external services (LLM endpoints, embedding/rerank services, internal IPs). If you supply LLM/embedding API keys or allow network egress, the skill will make outbound requests; audit those endpoints and restrict egress where appropriate. - Dependencies are extensive and pull third-party libraries. Pin and audit dependency versions, and install in an isolated virtualenv or container. - There are small inconsistencies (missing test module referenced in docs). Consider doing a quick code review of the text2sql and retriever modules and a dry-run in a non-production environment to confirm which external endpoints are actually called. If you need this skill in production: run it with network egress controls, a restricted DB user, and with LLM/embedding credentials limited to test models/services until reviewed.

Type: OpenClaw Skill Name: semantic-search Version: 1.0.0 The skill is classified as suspicious primarily due to a potential SQL injection vulnerability in `src/text2sql.py`. Although the `_is_valid_select_statement` function attempts to restrict SQL queries to `SELECT` statements and forbid DML/DDL commands, regex-based validation can be bypassed by sophisticated attackers, leading to unauthorized database operations. Additionally, the `PROJECT_CONFIG.md` file discloses internal network IP addresses for various services (e.g., FlightSQL, LLM, Embedding, Rerank, Nacos), which constitutes sensitive information leakage that could aid an attacker in internal reconnaissance. The skill also requires access to environment variables for sensitive credentials (database, LLM API keys) and performs external network calls, which, while necessary for its functionality, broaden the attack surface.