Security audit

抖音每日点赞飙升榜

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Douyin ranking lookup tool that uses a RedFox API key for read-only data queries, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you intend to use RedFoxHub for Douyin trend lookups. Store REDFOX_API_KEY as a secret or environment variable, do not paste real keys into chats or files, and confirm any subscription or daily push behavior before enabling it.

SkillSpector

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 (5)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The README explicitly tells users to invoke the skill with broad natural-language phrases like 'Show me today's Douyin surge ranking' and similar generic trending requests. This can cause over-triggering when a user is speaking generally about Douyin trends, leading to unintended skill activation, incorrect tool use, or unnecessary external API calls using the configured key.

Vague Triggers

Medium

Confidence: 77% confidence
Finding: Telling users to 'directly use natural language' with no activation boundaries makes skill triggering overly permissive and increases the chance of accidental invocation or prompt-routing abuse. In agent environments, broad trigger guidance can cause the skill to activate on ambiguous user requests and access external data or use configured secrets when the user did not clearly intend it.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: The trigger examples are common conversational phrases that overlap with normal chat, but the README provides no disambiguation rules or negative examples. This increases the risk of unintended activation, especially in multilingual or multi-skill environments where generic phrases like '看看今天的抖音飙升榜' may be matched too loosely and cause unnecessary external API calls or data disclosure in outputs.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The trigger list includes broad phrases such as '飙升榜' and '抖音新增', which can overlap with normal conversation and cause accidental invocation. Mis-triggering can unexpectedly send user queries to the external service and consume credentials or expose user intent without clear consent.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill tells users how to configure a live API key but does not warn that the key is sensitive, should not be pasted into chats, and must be stored securely. This increases the chance of credential leakage through logs, screenshots, shared config files, or improper handling by users and integrators.

Static analysis

No suspicious patterns detected.