65/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： clean

OpenClaw： suspicious

The skill's stated purpose (image grounding) is plausible, but the package includes unexpected large session logs, references to system config and internal model endpoints, and prompt‑injection indica...

[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": 1773909716294,
        "_id": "k9772ztqjw05nfsrbrcqzm6aw9836346",
        "changelog": "- Initial release of multimodal grounding skill using GLM-4.7V.\n- Supports detecting and locating objects, text, and UI elements in images with bounding box outputs.\n- Provides end-to-end workflow: model API call, bounding box parsing, and visualization on images.\n- Includes robust parsing for various bracket styles and auto-renormalization of coordinates.\n- Triggers automatically on grounding-related user requests in both English and Chinese.",
        "changelogSource": "user",
        "createdAt": 1773909716294,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "Ji Qi",
        "handle": "qijimrc",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/28889175?v=4",
        "kind": "user",
        "linkedUserId": "kn71qjx4x03f5hz846p4yvgygs82fadp"
    },
    "ownerHandle": "qijimrc",
    "skill": {
        "_creationTime": 1773909716294,
        "_id": "kd790wskkf73vz72y4qakbpgvd836htn",
        "badges": [],
        "canonicalSkillId": "kd70b2h1k4846ja193xn1vd8jx836md7",
        "createdAt": 1773909716294,
        "displayName": "vlm-grounding",
        "forkOf": {
            "at": 1773909716294,
            "kind": "duplicate",
            "skillId": "kd70b2h1k4846ja193xn1vd8jx836md7"
        },
        "latestVersionId": "k9772ztqjw05nfsrbrcqzm6aw9836346",
        "ownerUserId": "kn71qjx4x03f5hz846p4yvgygs82fadp",
        "slug": "vlm-grounding",
        "stats": {
            "comments": 0,
            "downloads": 36,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Use GLM-4.7V's multimodal grounding capability to detect and locate objects\/text in images. Activate when user asks to find, locate, detect, or ground specif...",
        "tags": {
            "latest": "k9772ztqjw05nfsrbrcqzm6aw9836346"
        },
        "updatedAt": 1774337878205
    }
}