ClawHub
Back to skill

Security audit

News - 热门新闻

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese news lookup wrapper that uses a disclosed JisuAPI key and network calls for its stated purpose.

Before installing, users should understand that news requests and the JISU_API_KEY are sent to JisuAPI, so they should only use an app key they are comfortable using with that third-party service. The skill otherwise appears narrowly scoped to fetching news and channel lists.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill declares it needs environment access and implicitly performs network calls via the referenced Python script and external API, but the manifest does not define an explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can let the runtime grant broader capabilities than reviewers or users expect.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The activation description and example utterances are entirely in Chinese and implicitly assume Chinese-language user requests. Under the policy, locale or language constraints should either be optional, user-selected, or clearly documented as region-specific; this file does not provide such an opt-in or justification.

External Transmission

Medium
Category
Data Exfiltration
Content
"time": "2016-03-16 07:23",
      "src": "中国网",
      "category": "mil",
      "pic": "http://api.jisuapi.com/news/upload/20160316/105123_31442.jpg",
      "content": "……",
      "url": "http://mil.sina.cn/zgjq/2016-03-16/detail-ifxqhmve9235380.d.html?vt=4&pos=108",
      "weburl": "http://mil.news.sina.com.cn/china/2016-03-16/doc-ifxqhmve9235380.shtml"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests


NEWS_GET_URL = "https://api.jisuapi.com/news/get"
NEWS_CHANNEL_URL = "https://api.jisuapi.com/news/channel"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests


NEWS_GET_URL = "https://api.jisuapi.com/news/get"
NEWS_CHANNEL_URL = "https://api.jisuapi.com/news/channel"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
This code includes natural-language descriptions, comments, and usage examples in Chinese without offering an alternative language or indicating that the skill is region- or language-specific. Under the language/locale policy, forcing a specific language in user-facing text without opt-in is a policy concern.

Static analysis

No suspicious patterns detected.