ClawHub
Back to skill

Security audit

新闻联播每日情报分析

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public CCTV news transcripts and helps turn them into a local report, with no evidence of hidden credential use, destructive behavior, or deceptive execution.

Before installing, be aware that this skill may fetch public CCTV pages and write Markdown reports locally, and optional daily scheduling or long-term note archival should only be enabled if you want persistent daily news records. Use explicit Xinwen Lianbo wording if you want to avoid accidental activation from generic news requests.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
代码与描述在“抓取央视官网官方文字稿、优先使用 day 日期页、当日可在晚间获取、输出到本地文件”等抓取层面基本一致；这些细节与描述中的“内置零依赖抓取脚本直取官网 day 日期页”相符。但描述的核心承诺是‘检索并分析’并产出结构化情报报告，而当前代码只是下载、清洗、去重并汇编原始文字稿到 Markdown。未见任何自然语言分析、分类、摘要、推演、信号提取或事实/观点分区实现。因此该代码块只覆盖了声明中的抓取子功能，未覆盖其主要宣称的分析与报告能力，构成实质性描述-行为不匹配。

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to use environment variables, write files, and fetch remote content, but it does not declare any explicit tool scope or permission boundaries. This creates an authorization gap where an agent runtime may grant broader-than-necessary capabilities, increasing the risk of unintended network access, file persistence, or misuse of ambient credentials.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The trigger phrases are broad enough that routine requests like '早报' or general policy/news questions could invoke this skill unexpectedly. Over-broad invocation can cause unintended network retrieval, external content processing, and file-writing behavior in contexts where the user did not specifically request this source or workflow.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill description is entirely framed around Chinese output and Chinese-language invocation phrases, but it does not state that the language is optional or user-selected. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless clearly justified as region-specific.

Static analysis

No suspicious patterns detected.