产品经理认知跃迁教练

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk coaching skill with no evidence of file access, credential use, persistence, or hidden execution.

Install if you want Chinese-language PM or career coaching. Be aware it may be invoked for broad advice-style prompts, so review whether its language and coaching scope match your intended use.

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
92% confidence
Finding
The trigger scope is broad enough to activate on generic requests for confusion, career advice, or product problems, which increases the chance the skill will intercept ordinary conversations outside a narrowly defined PM-coaching context. That can cause misrouting, over-application of the skill persona, and unintended coaching behavior when the user did not explicitly ask for this specialized workflow.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content is entirely in Chinese and presents a fixed interaction style without offering a language-choice mechanism. While not directly unsafe in the classic security sense, this can cause user-intent mismatch, misunderstanding of guidance, or exclusion of users who interact in another language, especially if the system auto-invokes the skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal