ClawHub
Back to skill

Security audit

抖音文案提取

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it fetches a user-provided Douyin link, extracts the caption text, creates a Word document, and sends it back.

Install only if you are comfortable with the agent fetching Douyin pages you provide and automatically returning a generated Word file. Avoid using sensitive or private links unless you are comfortable with that content being processed into a local temporary file and sent back through the chat. Install python-docx in a normal virtual environment rather than using the script's --break-system-packages suggestion.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger conditions are broad enough that normal user language about links, content extraction, or file creation could activate network retrieval and file-generation behavior unintentionally. In an agent environment, overbroad activation can cause unsolicited external requests and local file creation, which creates privacy, consent, and operational-risk issues.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill performs external fetching, parses potentially user-linked content, writes a DOCX file to local storage, and sends that file, but it does not disclose data handling boundaries or obtain explicit consent for these actions. This is dangerous because it can lead to unintended processing of third-party content, opaque retention in /tmp, and automatic exfiltration of generated files back through the messaging channel.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.