37°C Soother

Security checks across malware telemetry and agentic risk

Overview

This is a text-only quote-writing skill with no executable code, network behavior, credentials, persistence, or destructive capability.

Install only if you want this warm, reflective quote style to be available in your agent. It should not affect files or accounts, but its broad trigger language may make it activate for general emotional or topic prompts unless your agent requires explicit skill selection.

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
89% confidence
Finding
The trigger language is extremely broad ('any topic, emotion, or scene'), which can cause the skill to activate in many contexts beyond the user's clear intent. This is primarily a safety and routing issue: unintended activation may override more appropriate skills, produce irrelevant persuasive-style content, or interfere with user expectations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal