ClawHub

TikTok/Douyin 创作流水线

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises, but it includes an unsafe background transcription command and broad social-data scraping capabilities that need review before installation.

Install only if you are comfortable giving the agent a TikHub API key, making paid TikHub calls, downloading platform media, and collecting social-platform comments or user data. Avoid the CPU Whisper/background path until the shell=True nohup command is fixed, use a limited API key, monitor balance, and only collect data you are authorized to use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
log_file = f"/tmp/whisper_{os.path.basename(audio_path)}.log"
        nohup_cmd = f"nohup {' '.join(cmd)} > {log_file} 2>&1 &"
        print(f"🚀 Whisper 后台转写启动，日志: {log_file}")
        subprocess.run(nohup_cmd, shell=True)
        print(f"📝 文字稿将保存到: {output_path}")
        print(f"⏱️  medium 模型 CPU 转写 1 分钟音频约需 1-2 分钟，请耐心等待")
        return output_path
Confidence
99% confidence
Finding
subprocess.run(nohup_cmd, shell=True)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation text is broad enough to trigger on common requests involving videos, comments, user info, downloads, or TikHub API usage, which can cause the skill to activate outside narrowly intended contexts. Over-broad routing increases the chance that scraping, downloading, or transcription actions occur when the user did not specifically request those sensitive operations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill prominently supports scraping comments, retrieving user/follower-related data, and bulk downloading media, but provides no user-facing safeguards about privacy, consent, terms-of-service, or lawful use. In this context, omission of such warnings materially increases the risk of abusive collection of personal data and large-scale content extraction.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
openai-whisper
mlx-whisper
ffmpeg
Confidence
98% confidence
Finding
requests

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
openai-whisper
mlx-whisper
ffmpeg
Confidence
95% confidence
Finding
openai-whisper

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
openai-whisper
mlx-whisper
ffmpeg
Confidence
95% confidence
Finding
mlx-whisper

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
openai-whisper
mlx-whisper
ffmpeg
Confidence
84% confidence
Finding
ffmpeg

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
99% confidence
Finding
requests

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal