Brainstorm

Security checks across malware telemetry and agentic risk

Overview

This is a simple brainstorming helper that changes response style and structure without requesting code execution, credentials, persistence, or data access.

Reasonable to install for brainstorming assistance. If publisher provenance matters to you, verify the listing identity because the embedded metadata differs from the registry metadata.

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: 95% confidence
Finding: The phrase "Detect from context" creates an underspecified activation condition that can cause the skill to engage without an explicit user request. In an agent system, ambiguous triggering can lead to unintended mode selection, unexpected behavior changes, or interference with other skills, especially when the mode affects response style and decision framing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal