76/100 (Low)

OpenClaw： benign
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： benign

The skill's requirements and runtime instructions are coherent with its stated purpose (shadow-testing local Ollama models against cloud baselines); it needs local Ollama, Python, and Anthropic/OpenAI...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1774672905149,
        "_id": "k97bv6p2bx20bq73s8nve7fpnh83rqth",
        "changelog": "Add security_notes: no telemetry, all API calls use user's own keys, local Ollama never sends data externally",
        "changelogSource": "user",
        "createdAt": 1774672905149,
        "parsed": {
            "clawdis": {
                "emoji": "🧪",
                "primaryEnv": "ANTHROPIC_API_KEY",
                "requires": {
                    "bins": [
                        "ollama",
                        "python3"
                    ],
                    "env": [
                        "ANTHROPIC_API_KEY",
                        "OPENAI_API_KEY"
                    ]
                }
            }
        },
        "version": "1.2.2"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s17f2fw07zktjmcgagf5c29tbd83rt7v",
        "displayName": "Nissan Dookeran",
        "handle": "nissan",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/12583?v=4",
        "kind": "user",
        "linkedUserId": "kn72rbtybr3jzhcj2260qz6p2181x1mr"
    },
    "ownerHandle": "nissan",
    "skill": {
        "_creationTime": 1772098094518,
        "_id": "kd78r84e452r5hq37zqq1d0my981wyhq",
        "badges": [],
        "createdAt": 1772098094518,
        "displayName": "Llm Eval Router",
        "latestVersionId": "k97bv6p2bx20bq73s8nve7fpnh83rqth",
        "ownerPublisherId": "s17f2fw07zktjmcgagf5c29tbd83rt7v",
        "ownerUserId": "kn72rbtybr3jzhcj2260qz6p2181x1mr",
        "slug": "llm-eval-router",
        "stats": {
            "comments": 0,
            "downloads": 372,
            "installsAllTime": 2,
            "installsCurrent": 2,
            "stars": 0,
            "versions": 6
        },
        "summary": "Shadow-test local Ollama models against a cloud baseline with a multi-judge ensemble. Automatically promotes models when statistically proven equivalent — re...",
        "tags": {
            "latest": "k97bv6p2bx20bq73s8nve7fpnh83rqth"
        },
        "updatedAt": 1774759639215
    }
}