41/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： suspicious

The skill's declared requirements and install method partially match its purpose, but the SKILL.md expects provider credentials and environment variables that are not declared and there are minor meta...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1771886947306,
        "_id": "k97dbfjpxsn96ac4pr0r843ann81pdje",
        "changelog": "Initial release of tandemn-tuna — deploy and manage LLMs with serverless and spot GPU support.\n\n- Deploy HuggingFace models (Llama, Qwen, Mistral, DeepSeek, Gemma, etc.) to GPUs on Modal, RunPod, Cerebrium, Cloud Run, Baseten, and Azure with optional spot fallback.\n- OpenAI-compatible inference endpoint for every deployment.\n- Hybrid serverless + spot orchestration for cost savings and zero downtime.\n- Built-in commands for GPU price comparison, deployment management, status, and cost dashboard.\n- Provider setup guides for quick onboarding across all supported clouds.",
        "changelogSource": "auto",
        "createdAt": 1771886947306,
        "parsed": {
            "clawdis": {
                "emoji": "🐟",
                "homepage": "https:\/\/github.com\/Tandemn-Labs\/tandemn-tuna",
                "install": [
                    {
                        "bins": [
                            "tuna"
                        ],
                        "kind": "uv",
                        "package": "tandemn-tuna"
                    }
                ],
                "requires": {
                    "anyBins": [
                        "aws",
                        "az"
                    ],
                    "bins": [
                        "uv"
                    ]
                }
            }
        },
        "version": "0.0.1"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "Hetarth Chopra",
        "handle": "choprahetarth",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/34271010?v=4",
        "kind": "user",
        "linkedUserId": "kn7esackgc5h3kf78x3xcwr55981qnx9"
    },
    "ownerHandle": "choprahetarth",
    "skill": {
        "_creationTime": 1771886947306,
        "_id": "kd7602t2gkq2f78bh993rex9an81q4yy",
        "badges": [],
        "createdAt": 1771886947306,
        "displayName": "Tandemn Tuna Skill",
        "latestVersionId": "k97dbfjpxsn96ac4pr0r843ann81pdje",
        "ownerUserId": "kn7esackgc5h3kf78x3xcwr55981qnx9",
        "slug": "tandemn-tuna",
        "stats": {
            "comments": 0,
            "downloads": 353,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Deploy and serve LLM models on GPU. Compare GPU pricing. Launch vLLM on Modal, RunPod, Cerebrium, Cloud Run, Baseten, or Azure with spot instance fallback. O...",
        "tags": {
            "latest": "k97dbfjpxsn96ac4pr0r843ann81pdje"
        },
        "updatedAt": 1774326676275
    }
}