技能详情(站内镜像,无评论)
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v1.0.3
统计:⭐ 1 · 383 · 2 current installs · 2 all-time installs
⭐ 1
安装量(当前) 2
🛡 VirusTotal :可疑 · OpenClaw :良性
Package:ai4mse/navclaw
安全扫描(ClawHub)
- VirusTotal :可疑
- OpenClaw :良性
OpenClaw 评估
The skill's code, instructions, and required secrets line up with its stated purpose (Amap route planning and optional Mattermost delivery), but you should verify the upstream/source and be cautious about where you store API keys and bot tokens.
目的
NavClaw's described functionality (exhaustive routing using Amap, producing deep links, optional Mattermost posting) matches the code and runtime instructions. The Amap API key and optional Mattermost bot credentials are consistent with the stated features and are expected for the declared capabilities.
说明范围
SKILL.md instructs the agent/operator to check memory for an Amap API key, prompt the user, and/or write the key (and optional Mattermost config) into config.py; it also instructs calling wrapper.py and possibly uploading logs or sending messages to Mattermost. These actions are in-scope for a navigation skill, but they involve writing/storing secrets and sending files/messages to an external chat server. The agent is also instructed to update…
安装机制
There is no remote download/install step in the registry metadata; the package is instruction/code-bundle style with a small requirements.txt (requests). No third-party archive downloads or obscure URLs are used. Dependencies are minimal and proportional (only requests required).
证书
The registry lists no required env vars, and the skill expects users to populate API_KEY, MM_BASEURL, MM_BOT_TOKEN, and MM_CHANNEL_ID inside config.py. Those secrets are directly relevant: Amap key for routing queries and Mattermost token/URL/channel for message delivery. The number of credentials is appropriate for the feature set, but note they are stored in a config file (not environment variables).
持久
The skill does not request 'always: true' and uses normal autonomous invocation. However, SKILL.md explicitly recommends adding triggers to OpenClaw long-term memory / MEMORY.md to make invocation convenient; doing so gives the skill persistent triggerability within your agent. That is expected for an agent skill but is a privileged persistence decision you should consciously allow or avoid.
综合结论
This package appears to do what it says: it queries Amap, generates route candidates, and can post results to Mattermost. Before installing: 1) Verify the source (the skill claims a GitHub repo but the registry metadata lists source/homepage as unknown — confirm the upstream repo and review it yourself). 2) Only provide an Amap API key and Mattermost bot token if you trust the code and host; prefer creating a bot account with minimal privilege…
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「NavClaw」。简介:Smart driving — exhaustive route search, may outperform default navigation. 导航/…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/ai4mse/navclaw/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
暂无本地缓存内容,可在后台执行详情同步。