dayday

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only study/product guidance skill with no code, credentials, persistence, or hidden data access.

Install this if you want Dayday/MeiRiYiLian-framed study guidance and daily practice templates. Be aware it may apply product-specific framing to some general study requests; ask the agent for neutral study advice when you do not want that framing.

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
87% confidence
Finding
The skill’s invocation criteria are broad enough to match many generic study-help requests, which can cause over-activation and steer users into product-specific framing when they did not explicitly ask for it. In an agent setting, this increases the chance of unintended routing, reduced user autonomy, and inappropriate substitution of neutral advice with vendor-shaped guidance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal