41/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： unknown

OpenClaw： suspicious

The skill's core idea (use local Ollama models to peer-review cloud outputs) is coherent, but the instructions reference external workflows (Discord channels, a Reef API endpoint) and scripts that are...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1770927797485,
        "_id": "k974mhy52kmtn9cywzwyg5brjx810x04",
        "changelog": "Initial release — multi-model consensus layer using local LLMs via Ollama",
        "changelogSource": "user",
        "createdAt": 1770927797485,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "staybased",
        "handle": "staybased",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/216957304?v=4",
        "kind": "user",
        "linkedUserId": "kn77qz5f2w1rc1tqk6jbp538nn811405"
    },
    "ownerHandle": "staybased",
    "skill": {
        "_creationTime": 1770927797485,
        "_id": "kd7bdc58gybqnqb53c0tyrs5jx8106t1",
        "badges": [],
        "createdAt": 1770927797485,
        "displayName": "Peer Review",
        "latestVersionId": "k974mhy52kmtn9cywzwyg5brjx810x04",
        "ownerUserId": "kn77qz5f2w1rc1tqk6jbp538nn811405",
        "slug": "peer-review",
        "stats": {
            "comments": 0,
            "downloads": 663,
            "installsAllTime": 14,
            "installsCurrent": 11,
            "stars": 0,
            "versions": 1
        },
        "summary": "Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output.\nFan-out critiques to 2-3 local models, aggregate flags, synthesize consensus.\n\nUse when: validating trade analyses, reviewing agent output quality, testing local model accuracy,\nchecking any high-stakes Claude output before publishing or acting on it.\n\nDon't use when: simple fact-checking (just search the web), tasks that don't benefit from\nmulti-model consensus, time-critical decisions where 60s latency is unacceptable,\nreviewing trivial or low-stakes content.\n\nNegative examples:\n- \"Check if this date is correct\" → No. Just web search it.\n- \"Review my grocery list\" → No. Not worth multi-model inference.\n- \"I need this answer in 5 seconds\" → No. Peer review adds 30-60s latency.\n\nEdge cases:\n- Short text (<50 words) → Models may not find meaningful issues. Consider skipping.\n- Highly technical domain → Local models may lack domain knowledge. Weight flags lower.\n- Creative writing → Factual review doesn't apply well. Use only for logical consistency.",
        "tags": {
            "latest": "k974mhy52kmtn9cywzwyg5brjx810x04"
        },
        "updatedAt": 1774324383168
    }
}