安全扫描
OpenClaw
安全
high confidenceNULL
评估建议
This is an instruction-only, advisory skill and appears coherent. Proceeding to install poses minimal direct risk as-is. Before trusting future versions, review any added install steps, requested environment variables/credentials, or changes that would enable network downloads or persistent configuration; if you allow autonomous invocation, be aware the agent could use the skill without prompting, so restrict that if you prefer manual control.详细分析 ▾
✓ 用途与能力
The name/description (Agent discovery and evaluation) matches the SKILL.md examples. The skill declares no binaries, env vars, or config paths — which is appropriate for a purely advisory/search helper.
✓ 指令范围
SKILL.md contains only high-level examples of user prompts (search, compare, integration design, cost analysis). It does not instruct the agent to read files, access credentials, call external endpoints, or exfiltrate data.
✓ 安装机制
No install specification and no code files are present. As an instruction-only skill, it does not write code to disk or download artifacts.
✓ 凭证需求
No environment variables, credentials, or configuration paths are required — proportional to the stated advisory/search purpose.
✓ 持久化与权限
always is false (not force-included). The skill does not request persistent system modifications or access to other skills' configs. Normal autonomous invocation remains possible but is not excessive here.
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
latestv1.0.02026/4/10
NULL
● 无害
安装命令
点击复制官方npx clawhub@latest install skylv-agent-discovery
镜像加速npx clawhub@latest install skylv-agent-discovery --registry https://cn.longxiaskill.com