41/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： suspicious

The skill's purpose (scoring Langfuse traces using an OpenRouter judge) mostly matches what the code does, but there are multiple coherence and data-exfiltration risks — notably hardcoded Langfuse cre...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1771140092289,
        "_id": "k9760sebw2sa2007zts5bnm45s8178hg",
        "changelog": "LLM-as-a-Judge evaluator via Langfuse",
        "changelogSource": "user",
        "createdAt": 1771140092289,
        "parsed": {
            "clawdis": {
                "requires": {
                    "bins": [
                        "python3"
                    ],
                    "env": [
                        "OPENROUTER_API_KEY",
                        "LANGFUSE_PUBLIC_KEY",
                        "LANGFUSE_SECRET_KEY"
                    ]
                }
            }
        },
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "aiwithabidi",
        "handle": "aiwithabidi",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/208891229?v=4",
        "kind": "user",
        "linkedUserId": "kn78vyxbj9m9gk197mbwc6a6bh816qev"
    },
    "ownerHandle": "aiwithabidi",
    "skill": {
        "_creationTime": 1771140092289,
        "_id": "kd7es8a8a1ygjh64nmfxaed9yx816yd6",
        "badges": [],
        "createdAt": 1771140092289,
        "displayName": "LLM Evaluator Pro",
        "latestVersionId": "k9760sebw2sa2007zts5bnm45s8178hg",
        "ownerUserId": "kn78vyxbj9m9gk197mbwc6a6bh816qev",
        "slug": "llm-evaluator-pro",
        "stats": {
            "comments": 0,
            "downloads": 544,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 1,
            "versions": 1
        },
        "summary": "LLM-as-a-Judge evaluator via Langfuse. Scores traces on relevance, accuracy, hallucination, and helpfulness using GPT-5-nano as judge. Supports single trace...",
        "tags": {
            "evaluation": "k9760sebw2sa2007zts5bnm45s8178hg",
            "latest": "k9760sebw2sa2007zts5bnm45s8178hg",
            "quality": "k9760sebw2sa2007zts5bnm45s8178hg"
        },
        "updatedAt": 1774324886940
    }
}