Systems Thinking

Security checks across malware telemetry and agentic risk

Overview

This is a plain reasoning aid for systems-thinking analysis and does not request code execution, data access, persistence, or privileged behavior.

This skill should be safe to install as a response-structuring aid. Expect it to influence how the agent analyzes broad, interconnected problems; if it activates too often, disable it or narrow when you call it, but it should not gain access to files, credentials, services, or persistent state based on the reviewed artifacts.

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 description is intentionally expansive, covering vague requests like wanting to see 'how parts connect' or concern about 'unintended consequences' across many domains. That breadth can cause the skill to activate for a large class of ordinary analytical prompts, creating routing ambiguity and potentially overriding more specific skills or causing inconsistent behavior.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal