ASMR.one 音频下载器

• Outcome: Review
• Latest audit: May 28, 2026 at 8:39 AM UTC
• Version:
  1.0.0

Overview

This is mostly a normal ASMR.one downloader, but it includes an under-disclosed filename-obfuscation option framed as avoiding moderation.

Review before installing if you plan to use this with platforms that moderate filenames or media uploads. The normal download, compression, proxy, and local collection behavior is disclosed and proportionate, but avoid the obfuscation mode unless you have a legitimate local privacy need and understand the platform-policy and content-rights implications.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 82% confidence
• Finding: The skill documentation describes capabilities that require environment access, file writes, network access, and shell execution, but no explicit permissions are declared. This creates a transparency and consent problem: a user or platform may authorize the skill based on incomplete metadata while it performs broader system actions such as installing tools, writing config files, and contacting external services.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 87% confidence
• Finding: The declared purpose is narrow, but the documented behavior includes additional functions such as configuration management, network reachability testing, local file import, collection tracking, and use of multiple APIs. When a skill does substantially more than its top-level description suggests, users may be misled about the data it accesses and the operations it performs, increasing the risk of overbroad trust and unintended execution.

VirusTotal

66/66 vendors flagged this skill as clean.