Code 1.0.4

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed coding-workflow guide with optional local preference memory and no evidence of hidden network access, automatic execution, or destructive behavior.

Install this if you want a structured coding workflow and optional local preference memory. Do not save secrets, credentials, or sensitive personal data in ~/code/memory.md, and review or delete that file if you no longer want those preferences reused.

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: 89% confidence
Finding: The guidance says to plan when the user says "build", "create", or "implement", but these are very common verbs used in many ordinary requests. Without narrowing context or giving exclusions, the trigger condition is broad enough that the skill could activate in cases where explicit planning is not warranted.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal