📦 Child Learning Behavior Analysis Tool | 孩子学习行为分析工具 — 技能工具
v1.0.0Conducts video analysis of learning behavior for children/students, identifies poor learning habits, provides structured analysis reports and family educatio...
0· 18·0 当前·0 累计
by 安全扫描
OpenClaw
可疑
medium confidenceThe skill largely does what it claims (analyzes videos via a remote AI API) but contains several incoherent or risky choices: it will persist uploaded videos and local DB records, reads workspace-level config to obtain open-id/API endpoints, and its SKILL.md forbids reading local memory while the codebase reads/writes local config/DB — the user should review where data is sent and stored before installing.
评估建议
Key things to consider before installing or enabling this skill:
- Privacy: This skill uploads or causes remote downloads of user-supplied videos to external API servers (config references lifeemergence domains). Do not run with any real children's videos unless you trust those endpoints and have parental consent.
- Data storage: Uploaded videos and analysis records are persisted locally (attachments folder, SQLite DB in workspace/data). If you need ephemeral handling, run the skill in an isolat...详细分析 ▾
⚠ 用途与能力
The stated purpose (video-based child learning-behavior analysis) matches the code: scripts validate video files and call remote analysis APIs. However there are questionable requirements for obtaining open-id by reading config files in both the skill folder and the global workspace (${OPENCLAW_WORKSPACE}/skills/...). The SKILL.md forbids reading local memory files but the package includes DAO/SQLite and writes to workspace/data — this mismatch between declared constraints and actual file access is concerning.
⚠ 指令范围
Runtime instructions require saving uploaded videos to an attachments folder and explicitly mandate calling python -m scripts.study_analysis with an open-id and (optionally) api-key; the scripts will then upload the video or cause the remote service to download it. The SKILL.md also forbids using local memory but instructs to read configuration files for open-id, creating contradictory constraints. The agent will access filesystem paths and may transmit user videos and report metadata to external APIs.
ℹ 安装机制
There is no install spec (instruction-only in registry), but the skill bundle includes many Python modules and requirements files (skills/smyx_common and face_analysis). That means executing the skill will run bundled Python code that expects a populated Python environment; the absence of an explicit install step (or declared dependencies in the registry metadata) is a packaging inconsistency the user should be aware of.
⚠ 凭证需求
The skill declares no required environment variables, but the code reads environment variables (OPENCLAW_WORKSPACE, OPENCLAW_SENDER_OPEN_ID, etc.) and looks for config.yaml files (skills/smyx_common/scripts/config.yaml and workspace-level configs) to obtain open-id and API base URLs. The API base URLs in provided config point to external domains (lifeemergence.com and variants). Videos and report queries will be sent to remote endpoints; the skill can therefore exfiltrate sensitive video data and metadata despite not declaring credentials — this disparity is disproportionate and should be considered a privacy risk.
⚠ 持久化与权限
The code auto-saves uploaded attachments into an attachments directory and uses a local SQLite DB under a workspace data directory (skills/smyx_common dao logic). It therefore persists potentially sensitive videos and records across runs. The skill does not request always: true, but it does create and modify files in the workspace and can store user data locally and remotely.
⚠ skills/smyx_common/scripts/config-dev.yaml:2
Install source points to URL shortener or raw IP.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/15
- Initial release of the study-analysis skill for evaluating children's/student's learning behaviors via video analysis. - Identifies poor study habits (e.g., improper posture, distraction, fidgeting) and generates structured reports with improvement suggestions. - Enforces strict data access rules: all historical report queries must use the cloud API; local memory sources are strictly forbidden. - Requires open-id acquisition via a controlled workflow before any analysis; execution is paused and prompts the user if open-id is missing. - Outputs standardized Markdown tables for report listings, including direct report access links. - Provides parents with actionable family education suggestions grounded in educational psychology principles.
● 无害
安装命令
点击复制官方npx clawhub@latest install smyx-study-analysis
镜像加速npx clawhub@latest install smyx-study-analysis --registry https://cn.longxiaskill.com镜像同步中