Wit

Security checks across malware telemetry and agentic risk

Overview

WIT is a text-only product decision framework; its broad activation scope is worth noticing, but the artifacts do not request code execution, credentials, network access, persistence, or hidden authority.

Install this if you want the agent to apply a structured product-thinking and decision-review framework. Expect it to influence broad ideation, feature, planning, and strategy discussions; use a narrower skill when you need direct execution, implementation, or domain-specific controls.

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 skill description is extremely broad and can trigger on many vague ideation, planning, feature, project, process, and strategy requests. Overly broad routing increases the chance this skill is invoked instead of a more appropriate, narrower skill, which can cause unintended capture of user tasks, poor security boundary assumptions, and misleading guidance in contexts where stronger domain-specific controls should apply.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal