Brainstorm

Security checks across malware telemetry and agentic risk

Overview

This is a simple brainstorming guidance skill with no executable code, credential use, persistence, or system access.

This skill is reasonable to install if you want faster idea generation. If it chooses the wrong brainstorming style, explicitly ask for rapid fire, structured, deep dive, provocative, or collaborative mode.

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: 88% confidence
Finding: The phrase "Detect from context" is an ambiguous activation rule that can cause the skill to engage without a clear, user-requested trigger. In a multi-skill agent, this can lead to unintended activation, causing the assistant to switch into brainstorming behavior when the user wanted a different mode or more controlled output.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal