风险评分

94/100 (Very Low)

OpenClaw: benign
VirusTotal: benign
StaticScan: unknown

Reef Prompt Guard

作者: staybased
Slug:reef-prompt-guard
版本:1.0.0
更新时间:2026-02-26 07:10:36
风险信息

OpenClaw: benign

查看 OpenClaw 分析摘要(前 200 字预览)
This is a coherent prompt-injection detection skill whose code and docs align with its stated purpose; no unrelated credentials or installs are requested, though there are a few operational/security n...

[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": 1770927808691,
        "_id": "k97156kqhcyw9vf3t36waw3h4d810b84",
        "changelog": "Initial release — injection detection, 5 threat categories, CLI filter",
        "changelogSource": "user",
        "createdAt": 1770927808691,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "staybased",
        "handle": "staybased",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/216957304?v=4",
        "kind": "user",
        "linkedUserId": "kn77qz5f2w1rc1tqk6jbp538nn811405"
    },
    "ownerHandle": "staybased",
    "skill": {
        "_creationTime": 1770927808691,
        "_id": "kd79cq4heckxp5x0nv3esygb9d811a31",
        "badges": [],
        "createdAt": 1770927808691,
        "displayName": "Reef Prompt Guard",
        "latestVersionId": "k97156kqhcyw9vf3t36waw3h4d810b84",
        "ownerUserId": "kn77qz5f2w1rc1tqk6jbp538nn811405",
        "slug": "reef-prompt-guard",
        "stats": {
            "comments": 0,
            "downloads": 721,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Detect and filter prompt injection attacks in untrusted input. Use when processing external content (emails, web scrapes, API inputs, Discord messages, sub-agent outputs) or when building systems that accept user-provided text that will be passed to an LLM. Covers direct injection, jailbreaks, data exfiltration, privilege escalation, and context manipulation.",
        "tags": {
            "latest": "k97156kqhcyw9vf3t36waw3h4d810b84"
        },
        "updatedAt": 1772061036142
    }
}