家庭消费意图识别 - 从家庭聊天文本中识别消费意图，输出结构化JSON

This skill appears to do what it says: local classification of family-chat text into purchase-intent categories. Before installing/activating: (1) run it locally or inspect the code yourself—no hidden network calls were found; (2) avoid binding the Flask API to 0.0.0.0 or exposing it without authentication—bind to localhost or put it behind an authenticated proxy if you must provide remote access; (3) CORS is enabled by default in the sample, which allows cross-origin requests—remove or restrict CORS in production; (4) treat any processed chat data as sensitive personal data (do not send logs or inputs to third parties), and consider adding logging, rate-limiting, and input validation if you will run this as a long-lived service; (5) if you plan to change or extend the skill (add packages or an installer), re-evaluate for downloads, new dependencies, or added environment variables that could widen its privileges.

Type: OpenClaw Skill Name: family-intent-recognition Version: 1.0.0 The skill bundle is a legitimate rule-based NLP tool designed to identify family consumption intents from Chinese text. The core logic in `intent_classifier.py` uses keyword matching to categorize intents, while `api.py` and `cli.py` provide standard interfaces for the service. There is no evidence of data exfiltration, malicious execution, or prompt injection attempts in the code or documentation.