47/100 (Medium)

OpenClaw： suspicious
VirusTotal： suspicious
StaticScan： clean

OpenClaw： suspicious

The skill's stated purpose (testing model refusal to jailbreaks) broadly matches its instructions, but the runtime docs ask the agent to gather harmful seeds, use web/RAG capabilities, and produce exp...

[内容已截断]

VirusTotal： suspicious VT 报告

静态扫描： clean

No suspicious patterns detected.

README 未提供

{
    "latestVersion": {
        "_creationTime": 1774515061192,
        "_id": "k973x311xv4hgbcnz0s5zxp5p983ns4q",
        "changelog": "- Initial release introducing the \"adaptive-safety-refusal-integrity\" skill.\n- Enables testing of model refusal integrity against attempts to elicit harmful or forbidden information via creative writing or role-playing.\n- Defines real-world cases for detecting and refusing requests disguised using humor or insider role-play techniques.\n- Outlines a strict 3-phase pipeline for synthesizing evaluation data, with reference to guidance documents for each phase.\n- Focuses on upholding safety alignment and ethical boundaries across multiple risk categories despite user attempts to bypass safeguards.",
        "changelogSource": "user",
        "createdAt": 1774515061192,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s171v84p1hdytd53c4c49btymd83n2v2",
        "displayName": "TZWwww",
        "handle": "tzwwww",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/34390289?v=4",
        "kind": "user",
        "linkedUserId": "kn738wvgv50e0adqb45j5s399183n05e"
    },
    "ownerHandle": "tzwwww",
    "skill": {
        "_creationTime": 1774515061192,
        "_id": "kd7anshq3tp744qdd43b35nd4x83nzsy",
        "badges": [],
        "createdAt": 1774515061192,
        "displayName": "test-skill",
        "latestVersionId": "k973x311xv4hgbcnz0s5zxp5p983ns4q",
        "ownerPublisherId": "s171v84p1hdytd53c4c49btymd83n2v2",
        "ownerUserId": "kn738wvgv50e0adqb45j5s399183n05e",
        "slug": "adaptive-safety-refusal-integrity",
        "stats": {
            "comments": 0,
            "downloads": 26,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Use this skill when the user wants to test if the model can be tricked into giving out dangerous or forbidden information by using creative writing or 'actin...",
        "tags": {
            "latest": "k973x311xv4hgbcnz0s5zxp5p983ns4q"
        },
        "updatedAt": 1774515409341
    }
}