Back to skill

Security audit

What Is Agentpmt

Security checks across malware telemetry and agentic risk

Overview

This is an explanatory AgentPMT overview skill with no executable code, but following its linked setup paths can involve tokens, connected accounts, payments, and wallets.

Installing this skill appears low risk because it only explains AgentPMT and contains no code. Before following the referenced setup paths, review those separate skills, use least-privilege Agent Groups, protect bearer tokens, and be cautious with funded wallets or workflows that can act on connected accounts.

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

No suspicious patterns detected.