抖音每日点赞飙升榜

• Outcome: Pass
• Latest audit: Jun 4, 2026 at 8:54 AM UTC
• Version:
  1.0.1

Overview

This skill is a disclosed Douyin ranking lookup tool that uses a RedFox API key; its subscription wording is under-specified, but the artifacts do not show hidden persistence, exfiltration, or destructive behavior.

Install only if you trust RedFoxHub with your API key and the Douyin ranking queries you send. Treat the advertised subscription/push feature cautiously unless the platform provides clear opt-in, cancellation, delivery, and data-retention controls.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (3)

Description-Behavior Mismatch

Medium

• Confidence: 88% confidence
• Finding: The interaction guide introduces a subscription and scheduled push capability that is not part of the declared purpose of a ranking-query skill. This kind of scope expansion is dangerous because it can lead the agent to promise persistent data handling, notifications, or background actions that may bypass product controls, consent flows, or platform capability restrictions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill is invoked through broad natural-language phrases such as '飙升榜' and '抖音新增' without clear disambiguation rules, exclusions, or confirmation steps. This can cause accidental triggering in unrelated conversations, leading to unintended external API use, unexpected subscriptions, or disclosure of user intent/context to the third-party service.

Missing User Warnings

Medium

• Confidence: 76% confidence
• Finding: The skill claims subscription and scheduled push capabilities but does not explain what user data is stored, how consent is obtained, or what the delivery mechanism is. Any feature that persists preferences and sends recurring notifications creates privacy and consent risks if data handling is unspecified or implemented ad hoc.

VirusTotal

56/56 vendors flagged this skill as clean.