Self Aware Prediction System

Security checks across malware telemetry and agentic risk

Overview

This appears to be a guidance-only skill for predictions or judgments, with a broad trigger that users should apply carefully.

Install if you want a general-purpose prediction or judgment framework. Treat its outputs as reasoning support, not expert advice, and avoid relying on it alone for medical, legal, financial, safety-critical, or other high-stakes decisions.

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
93% confidence
Finding
The guide activates on broadly defined situations such as 'when needing to make a prediction or judgment,' which can apply to a very large range of ordinary user requests. Overly broad activation increases the chance the skill will trigger outside its intended scope, causing unintended behavior, overreach into sensitive decision-making, or user reliance on uncertain outputs in contexts that may require domain-specific safeguards.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal