# Send Safe Install to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "safe-install",
    "name": "Safe Install",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/mike007jd/safe-install",
    "canonicalUrl": "https://clawhub.ai/mike007jd/safe-install",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/safe-install",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-install",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "bin/safe-install.js",
      "fixtures/avoid-skill/SKILL.md",
      "fixtures/avoid-skill/package.json",
      "fixtures/avoid-skill/scripts/install.sh",
      "fixtures/caution-skill/SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "safe-install",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T12:13:28.230Z",
      "expiresAt": "2026-05-06T12:13:28.230Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-install",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-install",
        "contentDisposition": "attachment; filename=\"safe-install-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "safe-install"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/safe-install"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/safe-install",
    "downloadUrl": "https://openagent3.xyz/downloads/safe-install",
    "agentUrl": "https://openagent3.xyz/skills/safe-install/agent",
    "manifestUrl": "https://openagent3.xyz/skills/safe-install/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/safe-install/agent.md"
  }
}
```
## Documentation

### Safe Install

带安全策略的 OpenClaw Skill 安装器。

### 安全流程

来源验证: 检查是否在 allowedSources 白名单
模式阻断: 匹配 blockedPatterns 正则则拒绝
ClawShield 扫描: 自动扫描风险
风险分级审批:

Safe: 直接安装
Caution: 需确认 (--yes 或交互确认)
Avoid: 需 --force 强制安装


快照存储: 按 hash 存储版本，支持回滚

### 策略配置

.openclaw-tools/safe-install.json:

{
  "defaultAction": "prompt",
  "blockedPatterns": ["curl\\\\s*\\\\|\\\\s*sh"],
  "allowedSources": ["clawhub.com", "/local/skills"],
  "forceRequiredForAvoid": true
}

defaultAction: allow/prompt/block
blockedPatterns: 拒绝安装的正则列表
allowedSources: 允许的来源白名单
forceRequiredForAvoid: Avoid 级别是否必须 --force

### 用法

# 安装 skill（交互确认）
node bin/safe-install.js /path/to/skill --config ./policy.json --store ./.openclaw-tools/safe-install

# 自动确认 Caution
node bin/safe-install.js /path/to/skill --yes

# 强制安装 Avoid
node bin/safe-install.js /path/to/skill --force

# 查看安装历史
node bin/safe-install.js history --format table

# 回滚到上一版本
node bin/safe-install.js rollback my-skill

# 验证策略文件
node bin/safe-install.js policy validate --file ./policy.json

### 存储结构

.openclaw-tools/safe-install/
├── snapshots/{skill}/{version}/{hash}/  # 版本快照
├── active/{skill}/                       # 当前激活版本
├── state.json                           # 激活状态
└── history.json                         # 安装历史

### 安全限制

单文件最大 100MB
单 skill 最多 10000 个文件
单 skill 最大 500MB
路径遍历防护
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: mike007jd
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T12:13:28.230Z
- Expires at: 2026-05-06T12:13:28.230Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/safe-install)
- [Send to Agent page](https://openagent3.xyz/skills/safe-install/agent)
- [JSON manifest](https://openagent3.xyz/skills/safe-install/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/safe-install/agent.md)
- [Download page](https://openagent3.xyz/downloads/safe-install)