90/100 (Very Low)

OpenClaw： benign
VirusTotal： benign
StaticScan： suspicious

OpenClaw： benign

The skill's requests and behavior match its stated purpose (it sends text to promptinspector.io using a single API key); no surprising files, binaries, or privileged behavior were found.

VirusTotal： benign VT 报告

静态扫描： suspicious

Detected: suspicious.prompt_injection_instructions

README 未提供

{
    "latestVersion": {
        "_creationTime": 1774573000759,
        "_id": "k971ny3f3ej0kd7brsrew9q68583qk61",
        "changelog": "Initial release of Prompt Inspector, an API service for prompt injection detection.\n\n- Detects prompt injection, jailbreak attempts, and adversarial manipulations in user input.\n- Provides a safety verdict, risk score (0–1), and threat categories.\n- Supports both single-text and batch detection via CLI scripts (Python and Node.js).\n- Returns human-readable or JSON-formatted results.\n- Detects 10 distinct threat categories including instruction override, jailbreak, and asset extraction.\n- Requires an API key; supports environment variable or .env file configuration.",
        "changelogSource": "user",
        "createdAt": 1774573000759,
        "parsed": {
            "clawdis": {
                "emoji": "🛡️",
                "requires": {
                    "env": [
                        "PMTINSP_API_KEY"
                    ]
                }
            }
        },
        "version": "0.1.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s17d4c0apcbgaazxrfz3j22q7583pdgs",
        "displayName": "aunicall",
        "handle": "aunicall",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/266885561?v=4",
        "kind": "user",
        "linkedUserId": "kn73skms334yx4x0hk1axh7xwd82xbn5"
    },
    "ownerHandle": "aunicall",
    "skill": {
        "_creationTime": 1774573000759,
        "_id": "kd75p6be04wa3nmeyzwybvzpjd83qr9d",
        "badges": [],
        "createdAt": 1774573000759,
        "displayName": "Prompt Inspector",
        "latestVersionId": "k971ny3f3ej0kd7brsrew9q68583qk61",
        "ownerPublisherId": "s17d4c0apcbgaazxrfz3j22q7583pdgs",
        "ownerUserId": "kn73skms334yx4x0hk1axh7xwd82xbn5",
        "slug": "prompt-inspector",
        "stats": {
            "comments": 0,
            "downloads": 1,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Detect prompt injection attacks and adversarial inputs in user text before passing it to your LLM. Use when you need to validate or screen user-provided text...",
        "tags": {
            "latest": "k971ny3f3ej0kd7brsrew9q68583qk61"
        },
        "updatedAt": 1774573017495
    }
}