Security audit

Hot Topic Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for trend research, but it can use logged-in browser sessions and automatically save outputs to Tencent Docs from broad trigger phrases.

Review this skill before installing if you use logged-in Chinese social/content platforms or Tencent Docs. Prefer explicit prompts that name the skill, confirm before using profile="user", and confirm the Tencent Docs destination before saving or scheduling recurring runs.

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: 93% confidence
Finding: The trigger phrases include broad, ordinary-language requests such as '今天有什么热点' and '帮我看看最近什么火', which can plausibly appear in normal conversation and cause the skill to activate without the user explicitly intending to invoke it. Because the skill can perform web collection, use logged-in browser sessions, and save output to Tencent Docs, accidental activation can lead to unintended data access, external requests, and document creation.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README highlights Tencent Docs saving and optional logged-in browser scraping, but it does not present these as explicit user-risk warnings at the point of use. Users may not realize that invoking the skill can write generated content to a third-party service or access platform data through an authenticated browser profile, creating privacy, consent, and data-handling risks.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger phrases are broad and overlap with common conversational requests such as asking what is trending or what is popular recently. This can cause the skill to activate unexpectedly, leading to unintended web searches, browser-profile use, or automatic document creation without sufficiently explicit user intent.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill instructs use of xbrowser with profile="user" to access platform data via the user's logged-in browser session, but does not present a clear user-facing warning or consent gate. Because logged-in browser state may expose private account data, this omission can lead to unintended access to personal or account-scoped information.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The overview states that generated topic suggestions are automatically saved to Tencent Docs, but the skill metadata and trigger description do not clearly warn users about this external persistence behavior. Automatic saving can disclose sensitive prompts, research topics, competitive analysis, or account-linked data to a third-party document service without informed consent.

Static analysis

No suspicious patterns detected.