Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Video Classifier

v1.0.0

Classify unstructured long videos by selecting them in the backend and applying tags. Use when: user wants to classify videos, tag videos with specific label...

0· 59·1 current·1 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for wulooongcha/video-classifier.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Video Classifier" (wulooongcha/video-classifier) from ClawHub.
Skill page: https://clawhub.ai/wulooongcha/video-classifier
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install video-classifier

ClawHub CLI

Package manager switcher

npx clawhub@latest install video-classifier
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The skill name/description (video tagging) aligns with the runtime instructions to open the video management backend and apply tags. However, the metadata declares python3 as a required binary while the SKILL.md contains no Python usage or scripts; that discrepancy is unexplained and unnecessary for the described browser-driven workflow.
!
Instruction Scope
SKILL.md requires the agent to use the browser tool (chrome CDP) to log into a specific staff portal (https://staff.bluemv.net/d.php), set filters, select all matching videos, and perform bulk tagging and screenshots. This grants the skill access to the user's authenticated session, page content (potentially sensitive), and the ability to perform mass changes — actions that extend beyond simple read-only classification and could be destructive or leak data.
Install Mechanism
This is an instruction-only skill with no install spec or code to write to disk, which minimizes installation risk.
!
Credentials
No environment variables or credentials are declared, which is good, but the instruction to use the browser tool implies access to whatever session/cookies the browser profile has. The skill also requests taking screenshots and performing bulk operations; those actions can expose or change sensitive data. The declared python3 requirement is disproportionate and unexplained.
Persistence & Privilege
The skill is not always-enabled and is user-invocable (normal). However, the SKILL.md explicitly instructs the agent not to ask the user to perform manual steps, encouraging autonomous browser control — combine that with the ability to act on an authenticated staff portal and it increases the blast radius if misused. There is no evidence the skill modifies other skills or system config.
What to consider before installing
This skill automates clicks and screenshots inside an authenticated staff backend. Before installing, verify: (1) Why python3 is listed as required — ask the author for justification or remove it. (2) Whether you trust the skill and its maintainer to access your browser profile and authenticated session on https://staff.bluemv.net; the agent will be able to read pages and take screenshots. (3) Use a non-production/test account first to confirm behavior and prevent accidental mass edits. (4) Prefer requiring explicit user confirmation for each batch (do not allow fully autonomous runs that 'select all' and bulk-apply tags). (5) Ask for source/homepage or a vendor contact; absence of provenance increases risk. If you cannot validate these points, do not grant the skill browser automation privileges or avoid installing it.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎬 Clawdis
Binspython3
latestvk971sckgjpr4ye43mfkejagtg1850jyk
59downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

Video Classifier Skill

IMPORTANT: Use the browser tool to automate this workflow. Do NOT ask the user to do manual steps.

Backend Info

CRITICAL: Browser Automation Steps

You MUST use the browser tool (browser.profile.chrome) to complete this task:

  1. Navigate to backend: Use browser.navigate to open https://staff.bluemv.net/d.php

  2. Click menu: Use browser.click to:

    • Click [视频管理] menu
    • Select [小视频]
  3. Set filters: Use browser actions to:

    • Check 展示 → 显示
    • Select 类型 → 长视频
    • Select 结构 → 无结构视频
    • Set 刷新时间: 2023-01-10 to today
    • Fill 标签: [user-provided tag]
  4. Select all videos: Use browser.check to check all matching videos

  5. Submit: Use browser.click to:

    • Click [加入结构]
    • Select the tag
    • Click 确认 (Confirm)

Usage Examples

User: "帮我分类视频,标签是狼"
→ Execute with tag="狼"

User: "帮我分类20个视频,标签是狮子"  
→ Execute with tag="狮子", count=20

User: "今天分类200个老虎视频"
→ Execute with tag="老虎", count=200

Common Tags

狼、熊、狮子、老虎、大象、猴子、鸟类、水族、家禽、爬行动物

Notes

  • User must be logged in to https://staff.bluemv.net/d.php before starting
  • Process in batches of 50-100 for better reliability
  • Daily target: 200 video classifications
  • Take screenshots at key steps for verification

Comments

Loading comments...