Why We Live

Security checks across malware telemetry and agentic risk

Overview

This is a philosophical reflection skill with broad emotional triggers, but it does not request code execution, data access, persistence, or hidden authority.

Install this only if you want an optional philosophical lens for reflective conversations. Do not rely on it for crisis support, self-harm concerns, abuse or relationship safety, medical or legal decisions, or urgent practical help; in those cases use direct support and tell the agent not to apply this framework.

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: 94% confidence
Finding: The skill's description is extremely broad, covering existential questions, relationships, morality, suffering, death, and mental-health-adjacent distress. In an agent system, that broad trigger surface can cause over-invocation in sensitive situations, including crisis contexts where a philosophical reframing may be inappropriate or delay safer support-oriented handling.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The one-line invocation summary is also overly open-ended: 'existence, meaning, relationship, or self' and 'unshapen weight' are vague concepts that could match a large share of emotionally charged user conversations. That increases the chance the skill is selected for users in acute vulnerability, where its core design to avoid direct answers could conflict with the need for concrete safety guidance or referral.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal