47/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： clean

OpenClaw： suspicious

The skill largely matches its stated LoRA-training purpose, but multiple mismatches and hardcoded paths mean it is sloppy and may not behave as expected — review required before use.

VirusTotal： suspicious VT 报告

静态扫描： clean

No suspicious patterns detected.

README 未提供

{
    "latestVersion": {
        "_creationTime": 1773824672442,
        "_id": "k97e59pnxqhcv48am7v5vc07q9834rvj",
        "changelog": "Initial release of the lora-pipeline skill: end-to-end LoRA model training pipeline.\n\n- Automates the full process: photo collection, face verification, dataset scraping and cleaning, captioning, and LoRA training.\n- Each phase is modular and can be delegated to a sub-agent independently.\n- Includes strict privacy rules: no cloud uploads, all verifications run locally, never read or leak dataset contents.\n- Provides scripts for captioning, smart cropping, and batch training.\n- Ensures high-quality datasets: PNG format, 1024×1024 resolution minimum, no black borders, and enforced diversity.\n- Detailed directory structure and phase documentation for transparency and reproducibility.",
        "changelogSource": "auto",
        "createdAt": 1773824672442,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "iskWang",
        "handle": "iskwang",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/3337244?v=4",
        "kind": "user",
        "linkedUserId": "kn7bqxw7g2w0xc7r6j7pthw30s82q3br"
    },
    "ownerHandle": "iskwang",
    "skill": {
        "_creationTime": 1773824672442,
        "_id": "kd70jk6qf7fa81wfp5sgs2xgc9835x94",
        "badges": [],
        "createdAt": 1773824672442,
        "displayName": "Lora Pipeline",
        "latestVersionId": "k97e59pnxqhcv48am7v5vc07q9834rvj",
        "ownerUserId": "kn7bqxw7g2w0xc7r6j7pthw30s82q3br",
        "slug": "lora-pipeline",
        "stats": {
            "comments": 0,
            "downloads": 63,
            "installsAllTime": 1,
            "installsCurrent": 1,
            "stars": 0,
            "versions": 1
        },
        "summary": "Manages end-to-end LoRA training: collects and verifies photos, scrapes datasets, applies quality checks, captions, and trains the LoRA model locally.",
        "tags": {
            "latest": "k97e59pnxqhcv48am7v5vc07q9834rvj"
        },
        "updatedAt": 1774337047482
    }
}