Douyin Video Fetch

• Outcome: Pass
• Latest audit: May 28, 2026, 12:44 PM
• Version:
  1.0.0

Overview

This is a straightforward Douyin video downloader whose network access and local file writes match its stated purpose, with some ordinary CLI safety caveats.

Install only if you are comfortable with a Python downloader that launches a headless browser, contacts Douyin/video-hosting endpoints, reads any batch file path you provide, and writes MP4 files to the selected output directory. Use it only for videos you are authorized to download, choose a dedicated output folder, and avoid pointing --file at sensitive local files.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill advertises and invokes network access and local file writes/reads, but the metadata does not declare permissions or otherwise make those capabilities explicit. This creates a transparency and consent problem: an agent or reviewer may underestimate the skill's ability to fetch remote content and persist files locally, increasing the chance of unintended data access or filesystem modification.

Missing User Warnings

Low

• Confidence: 79% confidence
• Finding: The markdown instructs users to download Douyin videos to local storage without warning about local writes, copyright/terms-of-service issues, or privacy implications of storing third-party media. In this context, the skill is explicitly a downloader and material-ingestion step, so missing warnings and guardrails make misuse more likely even if the behavior is not inherently malicious.

VirusTotal

66/66 vendors flagged this skill as clean.