Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具

Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety...

This skill is not obviously malicious but has several red flags you should consider before enabling it: - Code reuse and scope creep: The package contains unrelated modules (face_analysis, pet-health docs) and a large shared library (skills/smyx_common). That may be benign reuse but increases the amount of code executed and any surprises. - File I/O and persistence: The skill will read/write config files and create a local SQLite DB under the workspace/data path and will save uploaded attachments to the skill directory. If you need to avoid local persistence, do not install or run it. - Network endpoints and API keys: The skill calls remote APIs (base URLs in skills/smyx_common/scripts/config.yaml point to lifeemergence domains). It will ask for an open-id (and optionally an API key). Do not provide real user identifiers, credentials, or sensitive data until you verify the backend endpoints and privacy policy. - Environment leakage: The code implicitly reads environment variables (OPENCLAW_SENDER_OPEN_ID, OPENCLAW_SENDER_USERNAME, FEISHU_OPEN_ID, OPENCLAW_WORKSPACE). If those exist in your environment they may be used automatically. - Minimal test recommendations: run the tool in an isolated sandbox workspace, with network egress blocked or pointed to a mock endpoint, and with empty/controlled OPENCLAW_WORKSPACE. Inspect (or prevent) the created config.yaml and sqlite DB. Review the actual API host addresses and confirm they are trusted before supplying real open-id or API keys. If you proceed, audit the code paths that perform HTTP requests (skills/smyx_common/scripts/api_service.py and scripts/api_service.py), decide where uploaded videos and generated reports will be stored, and confirm the remote service's data retention and privacy practices.

Type: OpenClaw Skill Name: smyx-child-dangerous-behavior-recognition-analysis Version: 1.0.0 The skill bundle implements a child safety monitoring system that analyzes video streams for hazardous behaviors via a remote API (lifeemergence.com). It utilizes a shared library (smyx_common) for managing authentication, local token storage in a SQLite database (smyx-common-claw.db), and cloud-based history retrieval. While SKILL.md contains high-priority instructions for the AI agent to ignore local memory files in favor of cloud data, and the code includes capabilities to recursively call the OpenClaw agent via subprocess (AgentSkill.ai_chat), these features appear to be legitimate architectural choices for maintaining data consistency and processing complex queries within the developer's ecosystem rather than indicators of malicious intent.