Security audit

china-briefing-资讯简报

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese news-briefing workflow that uses public web/news searches and a local helper script without persistence, credential access, or hidden execution.

Install this if you want Chinese-language briefings assembled from public news and social sources. Review cited sources before relying on conclusions, especially for social-platform content, and avoid including private or sensitive information in briefing prompts.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: 声明描述的是一个端到端的资讯简报生成技能：应能根据地理范围搜集新闻并输出简报。而实际代码仅完成前置的“尺度识别 + 搜索词推荐”功能，属于辅助模块，不是完整简报生成器。代码没有网络访问、没有外部依赖调用、没有内容抽取/去重/摘要/排版逻辑，因此其主要行为与声明的核心能力存在明显差异。尽管‘自动判断地理/行业尺度，推荐搜索策略’与声明中的场景部分相关，但仅能视为支持性子功能，不能覆盖所宣称的主要用途。

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The title and overall README describe the skill as producing a Chinese news briefing, but the document does not indicate that users can opt into another language or that Chinese-only output is a required, justified regional constraint. This can violate language/locale policy when a skill implicitly enforces one language for all users.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill description says it uses external sources and social platforms, but it does not prominently warn users at invocation time that content may be fetched from third-party sites. This can create privacy, consent, and trust issues because users may not realize their request will trigger browsing and aggregation from potentially unreliable or user-generated sources.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The description explicitly defines the skill as generating a Chinese briefing ("中文资讯简报生成") and the rest of the document is framed around fixed Chinese-language output. There is no indication that users can choose another language or opt into the locale constraint, which is a natural-language policy concern.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are very broad and overlap with common requests such as news, briefings, and summaries, which can cause the skill to activate unexpectedly. In a skill that pulls from external web and social sources, overbroad activation increases the chance of unrequested browsing, source mixing, and presentation of unverified content under an authoritative format.

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The document is entirely framed in Chinese and provides many Chinese-language search templates such as "中国 2026 最新政策经济" and localized China-specific geographic scopes down to street level, without stating that the skill is region-specific or that users may choose another language/locale. This can violate language/locale policy because it implicitly constrains usage to Chinese-language searches without explicit opt-in or justification.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: This markdown file contains user-facing natural language exclusively in Chinese, including headings, tables, and guidance, with no indication that Chinese is optional or that the skill is intentionally restricted to a Chinese-speaking context. The policy requires flagging language or locale constraints when a specific language is effectively forced without user opt-in.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: This file contains user-facing natural-language documentation and examples only in Chinese, which can amount to forcing a specific language without user opt-in. The policy allows locale constraints when they are explicitly documented and justified, but no such justification or language-choice mechanism is present here.

Static analysis

No suspicious patterns detected.