by 安全扫描
OpenClaw
安全
medium confidenceNULL
评估建议
This skill is instruction-only and appears to do what it says: it helps you switch between LLM providers configured in your OpenClaw CLI config. Before using it: (1) confirm you trust the OpenClaw CLI you have installed, (2) be aware the SKILL.md shows placing API keys in ~/.openclaw/openclaw.json (plaintext examples) — consider using a secure credential store or restricting file permissions (chmod 600) if you store secrets there, (3) verify the provider endpoints (baseUrl) are correct and trust...详细分析 ▾
✓ 用途与能力
Name/description (switching LLM providers) align with the instructions (use OpenClaw CLI and edit ~/.openclaw/openclaw.json). No unrelated credentials, binaries, or services are requested.
ℹ 指令范围
SKILL.md confines actions to switching providers and editing the user's OpenClaw config (~/.openclaw/openclaw.json). This is appropriate for the skill, but it does instruct storing API keys in a user config file (plaintext example), which has privacy/security implications outside the skill's control.
✓ 安装机制
Instruction-only skill with no install spec and no code files. Nothing will be written or executed by the skill itself during install.
✓ 凭证需求
The skill declares no environment variables or credentials. It expects API keys to be present in the user's OpenClaw config file, which is coherent with its stated function.
✓ 持久化与权限
always is false and it is user-invocable. The skill does not request elevated/persistent privileges or attempt to modify other skills or system-wide settings.
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
latestv1.0.02026/3/18
NULL
● 无害
安装命令
点击复制官方npx clawhub@latest install model-switch-skill
镜像加速npx clawhub@latest install model-switch-skill --registry https://cn.longxiaskill.com