Back to skill

Security audit

Analyst Relations Brief

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward analyst-briefing writing aid with no hidden execution, persistence, or data-transfer behavior in the artifact.

Before installing, users should be aware that the skill asks for business-sensitive briefing inputs such as roadmap themes, traction, customers, and analyst feedback, but its instructions explicitly say to flag confidential or unconfirmed information rather than expose or invent it.

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

No suspicious patterns detected.