Security audit

Skill Vetting (PhenixStar)

Security checks across malware telemetry and agentic risk

Overview

This skill is a local skill-vetting helper whose flagged content is security-pattern examples, not active harmful behavior.

Before installing, understand that this is a lightweight heuristic scanner, not a complete security guarantee. It will inspect files in directories you point it at and may produce false positives, including on its own example patterns, so treat results as review prompts rather than final truth.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution, suspicious.prompt_injection_instructions

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/scan.py:30

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: references/patterns.md:108