风险评分

65/100 (Medium)

OpenClaw: suspicious
VirusTotal: benign
StaticScan: clean

Feedback Learning V2

作者: Maxim Kravtsov
Slug:feedback-learning-v2
版本:2.0.0
更新时间:2026-03-21 05:00:13
风险信息

OpenClaw: suspicious

查看 OpenClaw 分析摘要(前 200 字预览)
The skill is mostly coherent with its stated purpose (local feedback logging and rule promotion) but contains a prompt-injection indicator in SKILL.md and instructs automatic capture of tool stderr/co...

[内容已截断]

VirusTotal: benign VT 报告

静态扫描: clean

No suspicious patterns detected.
README

README 未提供

文件列表

无文件信息

下载
下载官方 ZIP
原始 JSON 数据
{
    "latestVersion": {
        "_creationTime": 1774023780939,
        "_id": "k97e0tmqhkbg4nh89z0fwkcp098388q3",
        "changelog": "Version 2.0.0 of feedback-learning introduces major upgrades to feedback detection, tracking, and learning:\n\n- Now tracks both positive and negative patterns—positive triggers are analyzed and promoted alongside corrections.\n- Structured rules (genes) use a new detailed schema with condition, action, and context fields for clearer auto-promotion and diagnostics.\n- Adds lifecycle statuses for rules: active, stale, resolved, or wont-fix, with automatic resolution and stagnation checks.\n- Introduces a Behavioral Delta Test to ensure only meaningful rules are promoted.\n- Data files, cron integration, shell\/Python automation, and Russian\/English feedback detection are thoroughly documented and streamlined.\n- Weekly reporting and analysis are enhanced, including rule health and recurring pattern detection.",
        "changelogSource": "auto",
        "createdAt": 1774023780939,
        "version": "2.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "Maxim Kravtsov",
        "handle": "surdeddd",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/137003744?v=4",
        "kind": "user",
        "linkedUserId": "kn71n7a4hm759fm17m9p0ecstn839vx6"
    },
    "ownerHandle": "surdeddd",
    "skill": {
        "_creationTime": 1774023780939,
        "_id": "kd7478s6tg4c9tbgm92wc0emax838jt4",
        "badges": [],
        "createdAt": 1774023780939,
        "displayName": "Feedback Learning V2",
        "latestVersionId": "k97e0tmqhkbg4nh89z0fwkcp098388q3",
        "ownerUserId": "kn71n7a4hm759fm17m9p0ecstn839vx6",
        "slug": "feedback-learning-v2",
        "stats": {
            "comments": 0,
            "downloads": 29,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 0,
            "versions": 1
        },
        "summary": "Zero-LLM feedback learning system for OpenClaw agents. Detects user feedback (emoji reactions, text signals like \"переделай\"\/\"круто\"), logs events, tracks po...",
        "tags": {
            "latest": "k97e0tmqhkbg4nh89z0fwkcp098388q3"
        },
        "updatedAt": 1774040413444
    }
}