抖音每日热门作品榜

• Outcome: Pass
• Latest audit: Jun 4, 2026 at 8:52 AM UTC
• Version:
  1.0.0

Overview

This skill transparently queries Douyin ranking data from RedFox using a user-provided API key, with no evidence of hidden data access, persistence, or destructive behavior.

Install only if you are comfortable creating a RedFox API key and sending Douyin ranking queries to redfox.hk. Use explicit Douyin ranking phrases, avoid broad triggers like 'show all' by themselves, and confirm how any subscription feature would work before relying on it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 85% confidence
• Finding: The skill instructs use of an environment-sourced API key and outbound network access, but no permissions are explicitly declared. This creates a transparency and governance gap: a host may allow the skill to read secrets and call external services without users or policy engines seeing those capabilities up front.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The documented behavior does not match the implemented or implied behavior: it claims 30-day limits, subscriptions, and达人排名, while analysis indicates arbitrary date ranges, no actual subscription implementation, and extra output controls. Behavior/description mismatches are dangerous because they undermine user consent and policy review, and can expose more data or functionality than reviewers expect.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill tells users to invoke it with very broad natural-language phrases such as 'Today's ranking' or 'Show all', which are common in ordinary conversation and can accidentally trigger the skill outside of a clearly intended context. This increases the risk of unintended tool invocation, causing unexpected external API calls and disclosure of ranking data in situations where the user did not mean to use this specific skill.

VirusTotal

58/58 vendors flagged this skill as clean.