Back to skill

Security audit

Architecture Patterns

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent educational architecture-patterns bundle with examples and a local search helper, with no evidence of hidden or harmful behavior.

Reasonable to install after verifying the GitHub source and revision. Treat the Stripe/payment and credential-related snippets as teaching templates; add your own safeguards, test-mode defaults, and review before adapting them to a real application.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/clean-architecture-guide.md:387

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/hexagonal-architecture-guide.md:99