← Back to Skills Marketplace
noir-hedgehog

OpenClaw更新检查

by Noir · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
523
Downloads
0
Stars
8
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-update-check
Description
每日检查 OpenClaw 最新版本和 Release Note,分析更新必要性并推送详细更新建议给用户,不主动执行更新。
Usage Guidance
This skill appears to do what it says (check OpenClaw releases and recommend updates) but there are two important mismatches you should address before installing or enabling it: 1) The runtime instructions call the local 'openclaw' command, yet the skill metadata does not list any required binaries — confirm that the host will have the correct 'openclaw' binary and that you are comfortable allowing the agent to run it. 2) The skill promises to push recommendations via Feishu (feishu_doc/message) but declares no required environment variables or credentials — verify how Feishu authentication will be provided (API token, webhook, bot credentials), where those secrets will be stored, and who can read/send messages using them. Additional practical checks: - Ask the publisher (or inspect skill source) for details about Feishu integration and exact message endpoints; avoid providing global/overly-permissive tokens. - Prefer an implementation that requires explicit environment variables for Feishu and documents required binaries. - If you plan to run this on a schedule, configure the cron job yourself rather than relying on autonomous agent scheduling; ensure the agent's ability to run autonomously is limited if you don't want unattended pushes. - Because source/homepage is unknown, treat provenance as low: prefer skills from known publishers or require code inspection before granting message-sending privileges.
Capability Analysis
Type: OpenClaw Skill Name: openclaw-update-check Version: 1.0.0 The skill is designed to check for OpenClaw software updates by comparing the local version (via 'exec') with the latest release notes fetched from the official GitHub repository (via 'web_fetch'). It follows a transparent process of analyzing release notes and notifying the user via Feishu without performing any unauthorized actions or automatic updates. No indicators of data exfiltration, malicious execution, or prompt injection were found.
Capability Assessment
Purpose & Capability
The stated purpose (daily check of OpenClaw releases, summarize Release Notes, and push recommendations) is coherent with the instructions to call an 'openclaw' command, fetch GitHub releases, and send messages. However metadata lists no required binaries or credentials even though the SKILL.md explicitly relies on the local 'openclaw' executable and Feishu messaging; that's an unexplained omission.
Instruction Scope
SKILL.md instructs the agent to run 'openclaw update status' / 'openclaw version', to fetch GitHub releases (web_fetch), and to push results via Feishu (feishu_doc/message). The doc does not explain authentication for Feishu or how credentials are provided, and it does not declare that the host must have the 'openclaw' binary available. It also suggests configuring a daily cron job (persistence outside the agent). These gaps grant the skill discretion to execute local commands and send data externally without specifying how that external access is authorized.
Install Mechanism
Instruction-only skill with no install steps and no code files. This lowers install-time risk because nothing is written to disk by an installer. Runtime actions (exec/web_fetch) remain the primary surface.
Credentials
The skill will need Feishu credentials (API token/webhook) to push messages and relies on the local 'openclaw' binary, but requires.env is empty and required binaries lists none — a clear mismatch. Requiring no credentials while instructing outgoing messaging is disproportionate and under-specified.
Persistence & Privilege
always:false (good). SKILL.md suggests configuring a cron job for daily checks, which is an external persistence mechanism the user would set up. Agent autonomous invocation is allowed by default (disable-model-invocation:false) but that alone is not flagged — combine this with the missing credential declarations before allowing autonomous runs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install openclaw-update-check
  3. After installation, invoke the skill by name or use /openclaw-update-check
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Daily checks for new OpenClaw versions with automatic retrieval and analysis of Release Notes from GitHub. - Evaluates updates for significance: new features, security fixes, breaking changes, or important bug fixes. - Sends update recommendations and summaries to users via Feishu, clearly explaining reasons and version differences. - Can be triggered manually by user command or automatically via a scheduled task. - Only provides update suggestions—does not perform updates automatically.
Metadata
Slug openclaw-update-check
Version 1.0.0
License
All-time Installs 8
Active Installs 8
Total Versions 1
Frequently Asked Questions

What is OpenClaw更新检查?

每日检查 OpenClaw 最新版本和 Release Note,分析更新必要性并推送详细更新建议给用户,不主动执行更新。 It is an AI Agent Skill for Claude Code / OpenClaw, with 523 downloads so far.

How do I install OpenClaw更新检查?

Run "/install openclaw-update-check" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is OpenClaw更新检查 free?

Yes, OpenClaw更新检查 is completely free (open-source). You can download, install and use it at no cost.

Which platforms does OpenClaw更新检查 support?

OpenClaw更新检查 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created OpenClaw更新检查?

It is built and maintained by Noir (@noir-hedgehog); the current version is v1.0.0.

💬 Comments