风险评分

59/100 (Medium)

OpenClaw: suspicious
VirusTotal: benign
StaticScan: unknown

Sandwrap

作者: RubenAQuispe
Slug:sandwrap
版本:1.0.0
更新时间:2026-02-28 11:39:04
风险信息

OpenClaw: suspicious

查看 OpenClaw 分析摘要(前 200 字预览)
The skill's description matches its intent, but it claims code-level enforcement and filesystem/config behavior that are not present in this instruction-only package — the protections may be aspiratio...

[内容已截断]

VirusTotal: benign VT 报告

静态扫描: unknown

README

README 未提供

文件列表

无文件信息

下载
下载官方 ZIP
原始 JSON 数据
{
    "latestVersion": {
        "_creationTime": 1770438906987,
        "_id": "k97fcvbg7gsv5tg9q9pbvzt3wh80pcr0",
        "changelog": "Initial release: Soft-sandbox protection for running untrusted skills. 5 defense layers, 4 presets, ~85% attack prevention.",
        "changelogSource": "user",
        "createdAt": 1770438906987,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "RubenAQuispe",
        "handle": "rubenaquispe",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/44844199?v=4",
        "kind": "user",
        "linkedUserId": "kn73a46n97r1qndk66m8d9z3897zypjf"
    },
    "ownerHandle": "rubenaquispe",
    "skill": {
        "_creationTime": 1770438906987,
        "_id": "kd77r27g3z9hktq2vqpsqbfdad80qrea",
        "badges": [],
        "createdAt": 1770438906987,
        "displayName": "Sandwrap",
        "latestVersionId": "k97fcvbg7gsv5tg9q9pbvzt3wh80pcr0",
        "ownerUserId": "kn73a46n97r1qndk66m8d9z3897zypjf",
        "slug": "sandwrap",
        "stats": {
            "comments": 0,
            "downloads": 1473,
            "installsAllTime": 4,
            "installsCurrent": 4,
            "stars": 3,
            "versions": 1
        },
        "summary": "Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2) Processing untrusted content that might contain prompt injection, (3) Analyzing suspicious files or URLs safely, (4) Testing new skills before trusting them. Supports manual mode ('run X in sandwrap') and auto-wrap for risky skills.",
        "tags": {
            "latest": "k97fcvbg7gsv5tg9q9pbvzt3wh80pcr0"
        },
        "updatedAt": 1772249944816
    }
}