Security audit

Agent Security Patterns

Security checks across malware telemetry and agentic risk

Overview

This is an educational security-awareness skill with suspicious-looking phrases presented as examples, not as actions to perform.

This skill is reasonable to install as a reference for security review. Users should ensure agents treat the quoted commands, credential snippets, and prompt-injection phrases as educational examples only, not executable instructions.

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

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: SKILL.md:31