风险评分

41/100 (Medium)

OpenClaw: suspicious
VirusTotal: suspicious
StaticScan: unknown

AgentGuard Tech

作者: koshaji
Slug:agentguard-tech
版本:2.0.0
更新时间:2026-03-24 13:24:40
风险信息

OpenClaw: suspicious

查看 OpenClaw 分析摘要(前 200 字预览)
The skill's behavior mostly matches a security-wrapper tool, but there are notable inconsistencies and privacy/installation risks (automatic account creation, npm installs, unclear data sent off-agent...

[内容已截断]

VirusTotal: suspicious 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": 1772806617636,
        "_id": "k97cc0f3a2dcnbrr4vaxrpcpa182d6bn",
        "changelog": "v0.8.0: prompt injection detection, PII redaction, OWASP compliance, MCP policy, Slack HITL, multi-agent A2A",
        "changelogSource": "user",
        "createdAt": 1772806617636,
        "version": "2.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "koshaji",
        "handle": "koshaji",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/243474115?v=4",
        "kind": "user",
        "linkedUserId": "kn7127d5bj4zf03yaqxd3x68vd82dhe3"
    },
    "ownerHandle": "koshaji",
    "skill": {
        "_creationTime": 1772782518344,
        "_id": "kd7dvm7j8e46g0sdbhdsd6vzan82c7fb",
        "badges": [],
        "canonicalSkillId": "kd79vrwacw0pz7aphkmf4zgcnd82dkp2",
        "createdAt": 1772782518344,
        "displayName": "AgentGuard Tech",
        "forkOf": {
            "at": 1772782518344,
            "kind": "duplicate",
            "skillId": "kd79vrwacw0pz7aphkmf4zgcnd82dkp2"
        },
        "latestVersionId": "k97cc0f3a2dcnbrr4vaxrpcpa182d6bn",
        "ownerUserId": "kn7127d5bj4zf03yaqxd3x68vd82dhe3",
        "slug": "agentguard-tech",
        "stats": {
            "comments": 1,
            "downloads": 216,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 2
        },
        "summary": "Installs AgentGuard to secure your AI agent by wrapping tools with evaluate() to block prompt injections, tool abuse, and malicious commands.",
        "tags": {
            "latest": "k97cc0f3a2dcnbrr4vaxrpcpa182d6bn"
        },
        "updatedAt": 1774329880423
    }
}