Back to skill

Security audit

早播新闻

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple Zao Live share-link generator, with a minor risk that broad trigger phrases may route generic news or podcast requests to Zao Live.

Install this if you want common Chinese requests for listening to news or audio to generate Zao Live 早播 share links. If you only want Zao-specific activation, narrow the trigger wording before use; opening generated links may share normal visit data with Zao Live.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description advertises activation on very broad phrases like '听新闻' and similar generic requests for audio/news, which can cause the skill to trigger outside its intended scope. In an agent environment, overly broad routing can hijack unrelated user intents, leading to incorrect tool use, unwanted external requests, and unintended disclosure of third-party tracking data via generated share links.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The listed trigger phrases include generic requests such as '我要听新闻', '播一段新闻', '有什么新闻', and '推荐个播客', which are ambiguous and not clearly limited to this skill's specialized function. This increases the chance of misrouting common user requests into a third-party link-generation flow, causing confusing behavior, bypassing better-matched skills, and sending users to externally tracked content they did not specifically request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.