点教 Amulett

Security checks across malware telemetry and agentic risk

Overview

This skill is a low-risk meditation and reflection aid with local text content and a simple script that only prints prompts.

Install this only if you want its spiritual/reflection framing. Be aware that generic trigger words like “冥想”, “反思”, “NEO”, or “归一” may activate it during ordinary conversations; any future reminder or journal behavior should remain explicit and user-controlled.

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
95% confidence
Finding
The activation phrases are broad, common, and include ordinary words like “冥想” and “反思,” plus short tokens such as “NEO” and “归一,” which can plausibly appear in normal conversation. This can cause unintended skill activation, leading the agent to enter a spiritual-guidance mode without clear user intent and potentially interfere with unrelated interactions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal