← Back to Skills Marketplace
Pet Restricted Area Alert Skill | 宠物禁区预警技能
by
smyx-sunjinhui
· GitHub ↗
· v1.0.0
· MIT-0
64
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install smyx-pet-restricted-area-warning-analysis
Description
Monitors restricted area intrusions, climbing on dining tables, and rummaging through trash cans, and issues real-time alerts, suitable for home pet monitori...
Usage Guidance
This skill appears to implement the advertised pet-area video analysis and will send videos (or video URLs) to a remote API and produce structured reports. Before installing or running it, consider: 1) Privacy: videos you upload will be transmitted off-host to the configured API host (config YAML / ApiEnum base URLs). If you don't trust that remote service, do not upload sensitive footage. 2) Local persistence: the skill will save uploaded attachments to the skill directory and the common library can create a local SQLite DB under the workspace/data path — check and clean those directories if you have privacy concerns. 3) Undeclared env/config access: the code reads OPENCLAW_SENDER_OPEN_ID, OPENCLAW_SENDER_USERNAME, FEISHU_OPEN_ID and OPENCLAW_WORKSPACE and reads config YAML files in skills/smyx_common; these are not listed as required in the metadata. 4) Verify endpoints and provenance: the repo's configs reference lifeemergence/open API hosts — confirm the service owner and hosting domain before sending data. 5) If you need stricter guarantees: run the skill in an isolated environment, inspect skills/smyx_common/scripts/util.py (RequestUtil) to confirm exactly which endpoints and headers are used, and avoid providing an open-id or API key until you verify where data goes. If you want, I can: (a) list the exact env vars and files the code reads, (b) extract the API base URLs used at runtime from the config files, or (c) scan the util.RequestUtil implementation for any hardcoded or opaque network/exfiltration logic.
Capability Analysis
Type: OpenClaw Skill
Name: smyx-pet-restricted-area-warning-analysis
Version: 1.0.0
The skill bundle contains high-risk architectural patterns and aggressive prompt instructions. SKILL.md includes 'Mandatory Memory Rules' that explicitly forbid the AI agent from accessing its own local memory files or LanceDB, forcing reliance on a remote cloud API (lifeemergence.com). The Python scripts (notably scripts/util.py and scripts/dao.py) implement a complex authentication framework that performs 'silent registration' and maintains a local SQLite database (smyx-common-claw.db) to store user tokens. Furthermore, scripts/skill.py includes logic to execute shell commands via subprocess to recursively invoke the 'openclaw' agent, which significantly expands the potential for unintended command execution.
Capability Tags
Capability Assessment
Purpose & Capability
The name/description (pet restricted-area monitoring) matches the code and instructions: scripts upload or reference a video and call a remote analysis API, then format/report results. However the package includes a broad common library (skills/smyx_common) with local DB/DAO code and many dependencies that are heavier than strictly necessary for a simple client that posts a file to an API. That extra surface is explainable if this is part of a product suite, but it is broader than the single-purpose description.
Instruction Scope
SKILL.md explicitly forbids reading local memory files (memory/*.md, LanceDB) and mandates obtaining an open-id via config files or user-supplied value. The code does read config YAMLs (skills/smyx_common/scripts/config.yaml and the workspace config) and can also pick up environment variables (OPENCLAW_SENDER_OPEN_ID, OPENCLAW_SENDER_USERNAME, FEISHU_OPEN_ID) via ConstantEnum.init — these env reads are not declared in the skill metadata. The skill also auto-saves uploaded attachments into an attachments directory and will send video files (or their URLs) to remote API endpoints; sending user video off-host is expected for a cloud analysis skill but is a significant privacy action and is clearly called for in SKILL.md. The mismatch: relying on undeclared env vars/config files and persisting uploads locally are behaviors users should be explicitly warned about.
Install Mechanism
There is no install spec (instruction-only style), so nothing is downloaded or executed at install time beyond the provided code. This limits supply-chain risk from install-time fetches. The repository does contain requirements.txt in subpackages, but no automated installer is declared in the skill metadata.
Credentials
Declared requirements list no environment variables, but the code reads and uses several environment/config sources: OPENCLAW_SENDER_OPEN_ID, OPENCLAW_SENDER_USERNAME, FEISHU_OPEN_ID and OPENCLAW_WORKSPACE (used by DAO to build a data path). The SKILL.md mandates retrieving an open-id from skill config files or workspace config — that requires reading local files. Because no env/config requirements are declared in the metadata, these accesses are surprising. Also the skill will upload raw video files (potentially sensitive) to the remote API; that is necessary for cloud analysis but should be clearly documented and justified to the user.
Persistence & Privilege
The codebase includes a local SQLite DAO and utilities that create files under a workspace/data path (using OPENCLAW_WORKSPACE) and the skill promises to 'automatically save' uploaded attachments to an attachments directory. That means the skill persists user videos and may create/modify local DB files. The skill is not marked always:true, nor does it modify other skills' configs, but local persistence is broader than what a minimal analysis client would require and raises privacy concerns relative to the SKILL.md 'no local memory' rule (which forbids reading memory/*.md but does not forbid creating a local DB or attachments).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install smyx-pet-restricted-area-warning-analysis - After installation, invoke the skill by name or use
/smyx-pet-restricted-area-warning-analysis - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the pet restricted area warning analysis skill.
- Supports real-time detection and alerts for pets entering restricted zones, climbing dining tables, or rummaging through trash cans using computer vision algorithms.
- Enforces strict open-id verification with multi-step priority rules for secure API access.
- All historical report queries are exclusively retrieved from a cloud API; reading from local memory is strictly forbidden.
- Outputs structured alert reports, including Markdown tables with direct links to report images for easy review.
- Designed for home pet monitoring scenarios with easy integration of local or network video inputs.
Metadata
Frequently Asked Questions
What is Pet Restricted Area Alert Skill | 宠物禁区预警技能?
Monitors restricted area intrusions, climbing on dining tables, and rummaging through trash cans, and issues real-time alerts, suitable for home pet monitori... It is an AI Agent Skill for Claude Code / OpenClaw, with 64 downloads so far.
How do I install Pet Restricted Area Alert Skill | 宠物禁区预警技能?
Run "/install smyx-pet-restricted-area-warning-analysis" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pet Restricted Area Alert Skill | 宠物禁区预警技能 free?
Yes, Pet Restricted Area Alert Skill | 宠物禁区预警技能 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Pet Restricted Area Alert Skill | 宠物禁区预警技能 support?
Pet Restricted Area Alert Skill | 宠物禁区预警技能 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pet Restricted Area Alert Skill | 宠物禁区预警技能?
It is built and maintained by smyx-sunjinhui (@smyx-sunjinhui); the current version is v1.0.0.
More Skills