Use Cases

Security checks across malware telemetry and agentic risk

Overview

This is a text-only educational guide about practical AI use cases and does not ask for system access, credentials, background activity, or external actions.

This skill is reasonable to install as a general AI-use-case guide. Treat its privacy and pricing examples as general advice rather than guarantees for every AI service, and verify the current policy of any tool before entering passwords, API keys, confidential business data, customer data, or sensitive personal information.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The statement "Conversations aren't shared with others" is a broad natural-language claim about privacy behavior. In a skill file, this can violate organizational policy if the platform's actual data handling depends on product tier, settings, or jurisdiction, because it presents a universal guarantee without qualification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal