Defense

Security checks across malware telemetry and agentic risk

Overview

This is a text-only legal-defense guidance skill with no code, permissions, persistence, or data access, though its broad triggers may activate it in unrelated conversations.

This appears low-risk from a security and permissions standpoint. Before installing, remember it may activate from broad words like "defense," and because it concerns serious legal matters, use it to organize facts and prepare questions for qualified counsel in the relevant jurisdiction rather than as legal advice.

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: 90% confidence
Finding: This manifest file defines triggers such as "defense," "investigation," and "arrested," which are broad enough to overlap with everyday or non-legal contexts. The file does not provide narrowing conditions, context constraints, or negative examples to clarify when the skill should or should not activate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal