Back to skill

Security audit

thought-flow

Security checks across malware telemetry and agentic risk

Overview

This skill is a plainly disclosed collaboration workflow guide and does not add hidden code, privileged access, or data-handling behavior.

Before installing, understand that this skill may make the agent more structured about planning, asking for constraints, investigating failures, and proposing when to write durable project guidance. It does not appear to introduce hidden execution, credential use, background work, or external data sharing.

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

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.