china-briefing-资讯简报

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese news-briefing skill that uses public web sources and a small helper script, with no evidence of hidden access, persistence, credential use, or destructive behavior.

Install this if you want an agent to create Chinese news briefings from public web and social sources. Be aware that generic Chinese news or briefing requests may activate it, and review outputs for source quality, prompt-injection risk from web pages, and privacy sensitivity in very local community briefings.

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
84% confidence
Finding
The trigger phrases are extremely broad and overlap with ordinary user requests like '简报', '资讯', or '本地新闻', which can cause the skill to activate unexpectedly in contexts where the user did not intend web-sourced briefing behavior. In an agent environment, over-broad routing increases the chance of unintended external searches, content shaping, or invocation conflicts with other skills, which can lead to privacy leakage or unreliable outputs.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal