ClawHub

Ai News Zh

Security checks across malware telemetry and agentic risk

Overview

This skill transparently fetches public AI news, translates it into a Chinese digest, and can post it to user-configured chat channels.

Before installing or scheduling it, run it manually once, confirm whether the run previews or sends, verify the exact Feishu/Telegram/Discord destination, use narrowly scoped API keys, and keep any cron job easy to find and disable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The manual trigger phrase is very generic ('帮我采集今天的AI新闻，整理成中文日报'), which closely resembles an ordinary user request rather than a clearly scoped skill invocation. In environments that auto-match skills from natural language, this can cause unintended activation and downstream actions such as fetching content and preparing outbound messages without sufficiently explicit user intent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises scheduled collection and push delivery to external channels like Feishu, Telegram, and Discord, but it does not prominently warn that content will be transmitted off-platform. This creates a risk of users enabling automation without understanding that generated summaries or metadata may be sent to third-party services, increasing the chance of unintended data disclosure or policy violations.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal