65/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： clean

OpenClaw： suspicious

The skill's instructions mostly match its stated purpose (running A/B experiments), but there are a few mismatches and operational risks the author didn't declare — notably writing to persistent memor...

[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": 1774402677585,
        "_id": "k979dchmgmvrq47scjfkxzjbv583j86a",
        "changelog": "Initial release of ab-test-runner: a structured workflow for A\/B testing LLM prompts, agent behaviors, and content.\n\n- Guides users through hypothesis setup, variable selection, and metric definition.\n- Ensures standardized experiment design, including sample size rules and multi-dimensional rubrics.\n- Automates experiment execution via subagents, supports self\/cross\/external scoring.\n- Aggregates results, calculates effects, archives findings, and recommends next steps.\n- Includes detailed templates and pitfall documentation to improve testing consistency and result reliability.",
        "changelogSource": "auto",
        "createdAt": 1774402677585,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "s17fe775c9d5twmmpfa5wen3q983gcfx",
        "displayName": "demo112",
        "handle": "demo112",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/33809432?v=4",
        "kind": "user",
        "linkedUserId": "kn74vrjmq2se4vx6khxd9sxg3d81vp7f"
    },
    "ownerHandle": "demo112",
    "skill": {
        "_creationTime": 1774402677585,
        "_id": "kd75mtgakz0eeprpesc51119j183jmm3",
        "badges": [],
        "createdAt": 1774402677585,
        "displayName": "Ab Test Runner",
        "latestVersionId": "k979dchmgmvrq47scjfkxzjbv583j86a",
        "ownerPublisherId": "s17fe775c9d5twmmpfa5wen3q983gcfx",
        "ownerUserId": "kn74vrjmq2se4vx6khxd9sxg3d81vp7f",
        "slug": "ab-test-runner",
        "stats": {
            "comments": 0,
            "downloads": 0,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Design and execute A\/B testing experiments for LLM prompts, agent behaviors, and content production. Activate when user says \"run an AB test\", \"design an exp...",
        "tags": {
            "latest": "k979dchmgmvrq47scjfkxzjbv583j86a"
        },
        "updatedAt": 1774407109145
    }
}