新闻联播中翻中

Security checks across malware telemetry and agentic risk

Overview

This is a focused news-translation skill that fetches public CCTV transcripts, with only a minor risk of unintended activation from broad trigger words.

Safe to install as a public-news analysis helper. Invoke it with explicit terms like “新闻联播” or “央视新闻联播” to avoid accidental activation from the broader shorthand triggers.

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 list includes very short, ambiguous shorthand such as "联播" and "xwlb", which can cause the skill to activate for unrelated user requests. This is a real routing/overreach issue because an overly broad trigger can misclassify intent and pull in this skill when the user did not mean CCTV XinWenLianBo content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal