65/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： clean

OpenClaw： suspicious

The skill is coherent with its stated purpose (benchmark research and reporting) but the SKILL.md contains detected unicode-control characters (a prompt-injection signal) and the package comes from an...

[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": 1773487098884,
        "_id": "k9746zgdjj7ht7t94bkmkzq5mx82xe7c",
        "changelog": "Initial release of LLM Benchmark Analyst skill.\n\n- Enables searching and analysis of LLM benchmark results within a fixed, pre-approved benchmark universe.\n- Generates evidence-based reports on model strengths\/weaknesses, domain leaders, benchmark explanations, and predecessor comparisons.\n- Enforces strict normalization of model\/version and prioritizes official benchmark sources, with detailed provenance for every score.\n- Integrates workflow for benchmark selection, multimodal leaderboard extraction, overlap expansion, and defect warning application.\n- Outputs follow structured templates, always including scope, summary, evidence tables, comparisons, data defects, and exclusions.\n- Does not invent or guess missing data; maintains strict reporting fidelity and transparency.",
        "changelogSource": "user",
        "createdAt": 1773487098884,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "Chekhovin",
        "handle": "chekhovin",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/105915315?v=4",
        "kind": "user",
        "linkedUserId": "kn737qmf0p80bn8wtz7h2rrgr182wzp6"
    },
    "ownerHandle": "chekhovin",
    "skill": {
        "_creationTime": 1773487098884,
        "_id": "kd71ydjyz5dah7z8b41gpvdqd582x47a",
        "badges": [],
        "createdAt": 1773487098884,
        "displayName": "llm-benchmark-analyst",
        "latestVersionId": "k9746zgdjj7ht7t94bkmkzq5mx82xe7c",
        "ownerUserId": "kn737qmf0p80bn8wtz7h2rrgr182wzp6",
        "slug": "llm-benchmark-analyst",
        "stats": {
            "comments": 0,
            "downloads": 122,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "search and analyze llm benchmark results within a fixed benchmark universe, then produce evidence-based model strength and weakness reports or domain-leader...",
        "tags": {
            "latest": "k9746zgdjj7ht7t94bkmkzq5mx82xe7c"
        },
        "updatedAt": 1774333613217
    }
}