知识星球助手

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built for Knowledge Planet automation, but it can publish posts from a logged-in account without a clear final user confirmation.

Review before installing. Use only with the intended Knowledge Planet account, require the agent to show the target group and exact post content before publishing, and log out or clear the browser session when finished.

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
84% confidence
Finding
The trigger list includes broad everyday terms such as '发帖' and '星球登录', which can cause the skill to activate in contexts the user did not intend, especially when discussing posting or login generically. Because this skill can perform real external actions on zsxq.com, accidental invocation increases the risk of unintended navigation, login flow initiation, or content publication.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The instructions say posting should be completed directly without screenshots and do not warn that this immediately changes content on an external platform. In a skill that automates publishing, lack of explicit user confirmation and visibility before submission can lead to unintended or irreversible posts under the user's account.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal