Guangzhou Daily News

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:28 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed Guangzhou Daily news formatter with local Markdown output and optional scheduled/WeChat-style delivery behavior.

Install only if you want Guangzhou Daily/Xinhuacheng news saved under ~/News and possibly delivered on a schedule. Review any OpenClaw cron entries and any separate WeChat integration before authorizing recurring pushes or account access.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill declares behavior that writes Markdown files to the user's home directory and configures scheduled tasks, but no explicit permissions are declared. This creates a consent and transparency gap: an agent may perform persistent local actions without the user or platform having a clear permission boundary to review or enforce.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The description and usage examples use broad phrases like '获取广州日报新闻' and '获取广州最新新闻', which can overlap with ordinary requests for local news. This can cause unintended skill activation, leading to network access, file creation, and possible pushes when the user may have only wanted a general answer.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The manual invocation section reinforces generic prompts that do not clearly distinguish this skill from general news queries. In an agent ecosystem, ambiguous examples increase the chance of accidental invocation and unintended side effects such as scheduled fetches, file writes, or message pushes tied to this skill.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill advertises automatic scheduled fetching and WeChat push support but does not prominently warn users in the description that it may perform recurring background actions and outbound messaging. Lack of upfront disclosure undermines informed consent and can surprise users with persistent polling or external notifications.

VirusTotal

66/66 vendors flagged this skill as clean.