55/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： suspicious

OpenClaw： suspicious

The skill mostly implements the advertised multimodal features, but there are mismatches between its metadata, instructions, and runtime behavior (notably missing declared env vars, mixed TTS install ...

[内容已截断]

VirusTotal： benign VT 报告

静态扫描： suspicious

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.potential_exfiltration

README 未提供

{
    "latestVersion": {
        "_creationTime": 1774577277064,
        "_id": "k97a0m524ss7229ymbp2km9b8983pjgk",
        "changelog": "Initial release of Multimodal Base Skill.\n\n- Provides unified pipeline for image understanding (GPT-4V, OCR), speech recognition (Whisper), and speech synthesis (Edge TTS)\n- Supports flexible multimodal input\/output handling in one interface\n- Includes separate ImageProcessor, SpeechRecognizer, and SpeechSynthesizer modules\n- Offers configurable options including model, API key, language, and voice settings\n- Out-of-the-box support for 8 TTS voice types across 4 languages\n- Documentation and code examples for quick setup and API usage",
        "changelogSource": "auto",
        "createdAt": 1774577277064,
        "version": "0.1.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s173qtadqbwthef9dwg283f54n83np6t",
        "displayName": "yuyonghao-123",
        "handle": "yuyonghao-123",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/267580628?v=4",
        "kind": "user",
        "linkedUserId": "kn7b2av1gaq4ftrjvvs0454r4h833ftn"
    },
    "ownerHandle": "yuyonghao-123",
    "skill": {
        "_creationTime": 1774577277064,
        "_id": "kd79dnqeasgehpncnngavjq8th83pck7",
        "badges": [],
        "createdAt": 1774577277064,
        "displayName": "Multimodal Base",
        "latestVersionId": "k97a0m524ss7229ymbp2km9b8983pjgk",
        "ownerPublisherId": "s173qtadqbwthef9dwg283f54n83np6t",
        "ownerUserId": "kn7b2av1gaq4ftrjvvs0454r4h833ftn",
        "slug": "yuyonghao-multimodal-base",
        "stats": {
            "comments": 0,
            "downloads": 26,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Supports image understanding, OCR, speech-to-text, and text-to-speech synthesis with multi-voice and multimodal unified processing using OpenAI and Edge TTS.",
        "tags": {
            "latest": "k97a0m524ss7229ymbp2km9b8983pjgk"
        },
        "updatedAt": 1774577510027
    }
}