AgentBox Sandbox

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only AgentBox helper with no executable payload, but users should handle the credential examples carefully.

Safe to install as a text-only documentation skill. Before following its examples, verify package names against AgentBox's current official docs, avoid putting real passwords directly in command-line arguments, do not commit API keys to code, and prefer scoped environment variables or a secret manager for real credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation instructs users to pass their password directly on the command line via `agentbox auth login -u your_email -p your_password`. Command-line arguments are commonly exposed through shell history, process listings, audit logs, and CI job output, which can leak credentials to other local users or logging systems. In a support/reference skill, this is more dangerous because users may copy-paste the example verbatim into real environments.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The reference shows an API key being exported in the shell and hardcoded into Python example code without any warning about secret hygiene. Users may paste real keys into shell history, source files, notebooks, screenshots, or version control, leading to credential disclosure and unauthorized sandbox access. Because this skill is explicitly intended to answer operational how-to questions, examples are likely to be reused directly, increasing the chance of secret leakage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal