90/100 (Very Low)

OpenClaw： benign
VirusTotal： benign
StaticScan： suspicious

OpenClaw： benign

The skill's files, scripts, and instructions are coherent with its stated purpose (detecting and quarantining prompt-injection content); nothing requested is disproportionate or unrelated.

VirusTotal： benign VT 报告

静态扫描： suspicious

Detected: suspicious.prompt_injection_instructions

README 未提供

{
    "latestVersion": {
        "_creationTime": 1774666843714,
        "_id": "k970h18f52bjfpz32xbeateyvn83raps",
        "changelog": "Initial release focused on agent prompt injection defense.\n\n- Adds layered defense scripts: content tagging, scanning, memory write guardrails, and canary pattern detection.\n- New scripts for tagging untrusted input, scanning for attack patterns, and safely writing to memory.\n- Includes comprehensive checklist, hardening rules for agents, and practical usage examples.\n- Provides reference detection patterns and strong usage guidance for handling any untrusted external content.\n- Replaces the earlier prompt skill with a security-focused module.",
        "changelogSource": "user",
        "createdAt": 1774666843714,
        "parsed": {
            "clawdis": []
        },
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s171ayex7xgs1y9ggh92pfrnyx83scp4",
        "displayName": "AdrianTeng",
        "handle": "adrianteng",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/6933071?v=4",
        "kind": "user",
        "linkedUserId": "kn76xw2wtn0fdnz33vj6w7v4cs83rkzd"
    },
    "ownerHandle": "adrianteng",
    "skill": {
        "_creationTime": 1774666843714,
        "_id": "kd72vmpzs603wtm04t7tfw2pas83sf6g",
        "badges": [],
        "createdAt": 1774666843714,
        "displayName": "Prompt Injection Defense",
        "latestVersionId": "k970h18f52bjfpz32xbeateyvn83raps",
        "ownerPublisherId": "s171ayex7xgs1y9ggh92pfrnyx83scp4",
        "ownerUserId": "kn76xw2wtn0fdnz33vj6w7v4cs83rkzd",
        "slug": "prompt-injection-defense",
        "stats": {
            "comments": 0,
            "downloads": 18,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Harden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any ex...",
        "tags": {
            "latest": "k970h18f52bjfpz32xbeateyvn83raps"
        },
        "updatedAt": 1774666910913
    }
}