Security audit

Hot Aggregator Cn

Security checks for vulnerabilities and agentic risk

Overview

This skill appears safe to install, but its bundled aggregator uses static sample Chinese hot-topic data rather than live platform data.

Install only if you are comfortable with a lightweight Chinese-language demo-style aggregator. Do not rely on its output as current platform trends unless the publisher adds real data retrieval or clearly labels the results as sample data.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Intent-Code Divergence

Medium

Confidence: 90% confidence
Finding: The top-level documentation presents the file as a real all-platform aggregator, while the code immediately documents the dataset as simulated and never fetches external platform content. This is a meaningful intent mismatch because the documentation overstates what the tool actually does.

Description-Behavior Mismatch

Medium

Confidence: 98% confidence
Finding: The manifest describes an aggregator for Weibo, Zhihu, Baidu, Douyin, and Bilibili, implying retrieval and aggregation of current platform hot topics. In this file, all platform data is statically embedded under a comment explicitly stating '模拟各平台数据', so the script does not actually aggregate live or external platform data.

Vague Triggers

Low

Confidence: 78% confidence
Finding: The manifest description lists trigger phrases such as “热点聚合”, “热门汇总”, and “趋势分析”. Especially “趋势分析” and “热门汇总” are generic terms that could overlap with ordinary requests and the file does not define when the skill should or should not activate.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: This code includes user-facing strings, comments, and output primarily in Chinese, such as the title, platform names, and keyword-match message. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative locale or language selection is provided.