by 安全扫描
OpenClaw
可疑
medium confidenceThe skill is coherent with its stated purpose (creating/managing agent wallets) but relies on runtime npx execution of a Node package and instructs storing/reading sensitive secrets from disk, which raises operational and supply-chain risks the user should understand before enabling it.
评估建议
This skill appears to do what it claims, but it requires running a Node CLI via npx (which downloads and executes code from the npm registry) and it instructs you to store/read sensitive secrets (passwords, API keys, seed/backups) on disk for non-interactive use. Before installing or enabling: (1) review the npm package and the linked GitHub repo source code to ensure it is trustworthy; (2) avoid storing secrets in plaintext—use a secure secret manager or hardware key when possible and limit fil...详细分析 ▾
✓ 用途与能力
The name/description (agent crypto wallets) matches the instructions: provider selection, setup, balance, backup/recover, and non-interactive operation. Required binary (node) is reasonable for an npm CLI. No unrelated credentials or capabilities are requested.
ℹ 指令范围
The SKILL.md keeps to wallet-management tasks, but it explicitly instructs the agent/user to create and read sensitive files (password-file, api-key-file, e.g., ~/.secrets/*.txt) and to run non-interactive commands that could allow autonomous fund operations. These file reads/writes are functionally necessary but materially expand the trust surface (local secret storage, seed phrases, backups).
⚠ 安装机制
There is no packaged install spec in the registry; the skill expects use of `npx agentic-wallet`, which will fetch and execute an npm package at runtime. Dynamic npx/npm execution is a supply-chain risk because it runs external code that is not pre-vetted by the platform. The SKILL.md metadata also references installing the same Node package, reinforcing that code will be pulled from the public npm registry.
ℹ 凭证需求
The skill does not declare required environment variables (none listed) which matches the package being CLI driven, but it relies on local secret files (passwords, Crossmint API keys). Requesting these secrets is proportional to wallet management, yet storing them as plaintext under ~/.secrets and instructing automated non-interactive usage increases the risk of accidental exposure or misuse. No unrelated credentials are requested.
ℹ 持久化与权限
always:false and user-invocable:true are appropriate. However, autonomous model invocation is allowed (disable-model-invocation:false), and because the skill can create/use wallets and potentially send/receive funds, autonomous actions could have high impact. The skill does not request system-wide config changes or other skills' credentials.
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
latestv1.0.22026/3/30
Agentic Wallet 1.0.2 adds non-interactive Crossmint setup for fully automated agent workflows. - Added non-interactive Crossmint wallet creation using API key (no browser needed). - Expanded `setup` command options: now supports `--api-key-file`, `--chain-type`, and `--wallet-type` for Crossmint. - Updated documentation with new usage examples for non-interactive mode across providers. - No code changes; documentation improvements only.
● Pending
安装命令
点击复制官方npx clawhub@latest install agentic-wallet
镜像加速npx clawhub@latest install agentic-wallet --registry https://cn.longxiaskill.com