Real Skill packageSource verifiedClawHub registry

魔搭魔粒每日自动领取

自动领取魔搭(ModelScope)每日发放的魔粒(Magicube)算力额度。通过 Chrome DevTools Protocol 连接你自己已经打开的浏览器,在页面上点击「领取」按钮,并以余额前后差值作为唯一成功判据(余额没变一律记 UNKNOWN,不报成功)。不调用非公开接口,不修改浏览器文件,不启动或结束任何浏览器进程;只操作 modelscope.cn 域名下的页面,点击前在页面内原子复核 host(校验与点击同一次 JS 执行,标签页离开魔搭就一个按钮都不点)。含人工登录一次的说明、四态判据机、故障处置表与本地自测脚本。当用户说「领魔粒」「魔搭签到」「魔粒余额」「魔搭自动登录」「ModelScope checkin」「魔粒够不够」时使用。

Identity and source

Publisher attributionrobinregistry owner unverified by skillvetai
Functional categoryBrowser Automation & RPAautomatically inferred · 56% rule confidence
Package forminstruction with code7 recorded files
Canonical sourceClawHub registryclawhub:oracis:modelscope-magicube-checkin
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/2/2026.claude/skills/modelscope-magicube-checkin

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/2/2026.agents/skills/modelscope-magicube-checkin

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/2/2026skills/modelscope-magicube-checkin

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @oracis/modelscope-magicube-checkin
clawhub inspect @oracis/modelscope-magicube-checkin --version 1.3.3

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
7 / 7 inspected as text
Checked
11/2/2026, 9:47:36 PM
Scanner
0.1.3
Policy
1.0.3
4 automated findings
highDynamic code or shell execution is presentscripts/ms_cdp.py:343 · confidence 78%eval(
highDynamic code or shell execution is presentscripts/ms_checkin.py:332 · confidence 78%eval(
highDynamic code or shell execution is presentscripts/selftest.py:129 · confidence 78%eval(
highEncoded content is decoded and executedscripts/ms_cdp.py:40 · confidence 90%base64
4 High/Critical review queue entries
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
7 dependency and API indicators
  • api: attacker.modelscope.cn.evil.com
  • api: clawhub.ai
  • api: developer.chrome.com
  • api: evil-modelscope.cn
  • api: evil.example.com
  • api: modelscope.cn
  • api: www.modelscope.cn
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/2/2026, 7:28:09 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:193b9e22180a4e245a77090296d9ec4e73967606e71b76cd9aaa459689a341ca
Show up to 7 recorded paths
  • manifest.yaml
  • scripts/ms_cdp.py
  • scripts/ms_checkin.py
  • scripts/run_selftest.py
  • scripts/selftest.py
  • skill-card.md
  • SKILL.md

Source changelog

v1.3.3: remove the page-writable host override, which was itself a backdoor. The ClawHub security review of v1.3.2 flagged two issues. First: the skill can be tricked into clicking on another website - the root cause was a window.__msCurrentHost override added for testability, which any page (including a malicious one) could set to www.modelscope.cn to impersonate the real site. That channel is now gone: the host check reads location.hostname only, which a page cannot forge. The self-test now builds a real-host fake page by navigating to the genuine domain and swapping the DOM with Page.setDocumentContent, so no forgeable hook is needed. A new adversarial case sets every host override variable on the page and still asserts that the click is refused and location.hostname is unchanged. Second: the optional test launcher exceeded its advertised browser restrictions - it used subprocess.Pop…

Release security diff

highCompared fixed releases 1.3.1 and 1.3.3; 0 finding and 1 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Permission escalation detected
Change reasons and limitations
  • new sensitive permission
  • permission surface changed
  • dependency surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

1.3.111/2/2026sha256:e2832b52b6018d39f6c0aa4a952831b9f570fbe0c4ac7c39cb98e87e07233266