ClawHub

ai-news

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward daily-news lookup tool that only calls a disclosed third-party news API and does not access local files, credentials, or persistent settings.

Install it if you are comfortable with api.cjiot.cc receiving the dates or article IDs you request. Treat returned article content as untrusted news text, not as instructions for your agent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger conditions are overly broad, including generic keywords like “新闻”, “日报”, and “头条”, which can overlap with normal conversation and cause unintended skill activation. In an agent environment, this can lead to unsolicited outbound requests to the external news API and inappropriate context switching away from the user’s actual task.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal