65/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： clean

OpenClaw： suspicious

The SKILL.md asks the user/agent to install external Python packages and supply multiple API keys and will send queries/responses to third‑party endpoints, but the registry metadata declares no requir...

[内容已截断]

VirusTotal： benign VT 报告

静态扫描： clean

No suspicious patterns detected.

README 未提供

{
    "latestVersion": {
        "_creationTime": 1773663261582,
        "_id": "k973dmxdx34yhy98bh2am84p6h83034z",
        "changelog": "Initial release of Auto Arena: end-to-end automated arena evaluation and ranking for AI models or agents.\n\n- Automatically generates test queries and evaluation rubrics from your task description.\n- Concurrently collects responses from multiple model endpoints; supports at least 2 models or agents.\n- Uses a strong judge model to run pairwise, position-bias-mitigated comparisons across all models.\n- Produces win-rate rankings, bar charts, optional heatmaps, and full Markdown reports.\n- Resumable, supports incremental endpoint addition, checkpointing, and judge model hot-swap.\n- Provides both CLI and Python API usage with extensive configuration and customization options.",
        "changelogSource": "user",
        "createdAt": 1773663261582,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "helloml0326",
        "handle": "helloml0326",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/18115084?v=4",
        "kind": "user",
        "linkedUserId": "kn70mnwvmpcpfk1j851py1f19x830cqg"
    },
    "ownerHandle": "helloml0326",
    "skill": {
        "_creationTime": 1773663261582,
        "_id": "kd7ft74pfq060j0d24g02pcxa18310ps",
        "badges": [],
        "createdAt": 1773663261582,
        "displayName": "Auto Arena",
        "latestVersionId": "k973dmxdx34yhy98bh2am84p6h83034z",
        "ownerUserId": "kn70mnwvmpcpfk1j851py1f19x830cqg",
        "slug": "auto-arena",
        "stats": {
            "comments": 0,
            "downloads": 109,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects resp...",
        "tags": {
            "latest": "k973dmxdx34yhy98bh2am84p6h83034z"
        },
        "updatedAt": 1774248796040
    }
}