Back to skill

Security audit

AgentPost200

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward guide for using the AgentPost200 mailbox API, with disclosed network use and credential handling that fit its purpose.

Install only if you want an external hosted mailbox for agent messages. Treat the API key as a secret, share the inbound post URL only with intended senders, and review any optional webhook forwarding URL before enabling 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.