41/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： suspicious

The skill's description and runtime instructions claim a networked npm package that automatically reports detected prompt patterns, but the registry entry contains no code or install spec, no declared...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1770051173632,
        "_id": "k975fn9yc1gwgmxfmcvm44dxr580dqgh",
        "changelog": "- Initial release of HiveFence v1.0.0\n- Collective prompt injection defense network for AI agents; immunity spreads to all when one agent detects a threat\n- Real-time, multi-language attack detection (EN, KO, JA, ZH) with <50ms response\n- Community voting system for validating new attack patterns\n- Privacy-preserving threat sharing using SHA-256 hashes\n- Risk-based prioritization with severity scoring\n- Fast, edge-first deployment on Cloudflare Workers (300+ locations)\n- Public API endpoints for threat submission, voting, and statistics",
        "changelogSource": "auto",
        "createdAt": 1770051173632,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "seojoonkim",
        "handle": "seojoonkim",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/2534327?v=4",
        "kind": "user",
        "linkedUserId": "kn7dtr5re5ct7n6pesc32j25qs8054r6"
    },
    "ownerHandle": "seojoonkim",
    "skill": {
        "_creationTime": 1770051173632,
        "_id": "kd7aqrhkj4n099sby97a234g1h80c68m",
        "badges": [],
        "createdAt": 1770051173632,
        "displayName": "HiveFence",
        "latestVersionId": "k975fn9yc1gwgmxfmcvm44dxr580dqgh",
        "ownerUserId": "kn7dtr5re5ct7n6pesc32j25qs8054r6",
        "slug": "hivefence",
        "stats": {
            "comments": 0,
            "downloads": 1735,
            "installsAllTime": 3,
            "installsCurrent": 3,
            "stars": 0,
            "versions": 1
        },
        "summary": "Collective immunity network for AI agents. When one agent detects a prompt injection attack, all connected agents become immune. Real-time pattern detection, community voting, and distributed threat intelligence. Built on top of prompt-guard.",
        "tags": {
            "latest": "k975fn9yc1gwgmxfmcvm44dxr580dqgh"
        },
        "updatedAt": 1774322263841
    }
}