Parkinson's & Epileptic Behavior Recognition Skill | 帕金森癫痫行为识别技能

Identifies abnormal behaviors such as limb tremors, convulsions, stiffness, and gait abnormalities through video recognition, assisting in home risk monitori...

Before installing or running this skill, consider the following: (1) Source provenance — the package has no homepage and an unknown owner; verify the author or run in an isolated/test environment. (2) Data flows — the skill uploads videos (potentially sensitive medical/home videos) to external APIs (config points to lifeemergence domains); review and confirm the destination, privacy policy, and whether an API key is required. (3) Undeclared env/config usage — the code reads OPENCLAW_WORKSPACE, OPENCLAW_SENDER_OPEN_ID, FEISHU_OPEN_ID and local config files; ensure these values are safe to expose and inspect skills/smyx_common/scripts/config.yaml and prod/test configs before use. (4) Local persistence — uploads/attachments and a SQLite DB are written into workspace data; if that is undesired, run in a sandbox or modify the code. (5) Dependency surface — a large requirements file is present; installing dependencies may bring in many packages. (6) Test with non-sensitive dummy videos and confirm where data is transmitted and stored; request the vendor/source to provide explicit API endpoint and data-retention details. If you cannot validate these points, avoid using with real patient data.

Type: OpenClaw Skill Name: smyx-parkinson-epilepsy-behavior-recognition-analysis Version: 1.0.0 The skill bundle implements a complex health monitoring system with several high-risk patterns. It uses `subprocess.run` to execute recursive `openclaw agent` commands (in `skills/smyx_common/scripts/skill.py`), maintains a local SQLite database (`smyx-common-claw.db`) to persist user tokens and session data (in `scripts/dao.py`), and contains aggressive prompt instructions in `SKILL.md` that force the AI agent to ignore its standard memory systems in favor of the developer's remote API. Additionally, `RequestUtil` automatically transmits user identifiers (open-id/mobile) to a remote endpoint (`lifeemergence.com`) to fetch and store authentication tokens. While these behaviors are technically aligned with the stated purpose of cloud-based medical analysis, the combination of recursive execution, local credential persistence, and restrictive prompt instructions is highly irregular.