41/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： suspicious

The skill mostly fits its stated purpose (evaluating Langfuse traces via OpenRouter) but contains unexpected behaviors—hardcoded Langfuse API keys in code and an undeclared read of a user-local .env f...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1772679152872,
        "_id": "k97dkbkdwj5rj6se65bea0x1w582b0ww",
        "changelog": "- Initial release of the llm-evaluator skill.\n- Provides an LLM-as-a-Judge system for evaluating AI outputs using relevance, accuracy, hallucination, and helpfulness scores.\n- Integrates with Langfuse and uses GPT-5-nano for efficient automated judging.\n- Enables batch backfill scoring for historical traces and real-time evaluation of outputs.\n- Command-line interface for testing, scoring specific traces, and running backfills.",
        "changelogSource": "auto",
        "createdAt": 1772679152872,
        "parsed": {
            "clawdis": {
                "emoji": "⚖️",
                "homepage": "https:\/\/www.agxntsix.ai",
                "primaryEnv": "OPENROUTER_API_KEY",
                "requires": {
                    "env": [
                        "OPENROUTER_API_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": 1772679152872,
        "_id": "kd72v6yqwgdtpsy97hq6nct43n82bzrc",
        "badges": [],
        "createdAt": 1772679152872,
        "displayName": "Llm Evaluator",
        "latestVersionId": "k97dkbkdwj5rj6se65bea0x1w582b0ww",
        "ownerUserId": "kn78vyxbj9m9gk197mbwc6a6bh816qev",
        "slug": "llm-evaluator",
        "stats": {
            "comments": 0,
            "downloads": 203,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "LLM-as-a-Judge evaluation system using Langfuse. Score AI outputs on relevance, accuracy, hallucination, and helpfulness. Backfill scoring on historical trac...",
        "tags": {
            "latest": "k97dkbkdwj5rj6se65bea0x1w582b0ww"
        },
        "updatedAt": 1774329329486
    }
}