Pub

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for using the Pub CLI to create, publish, update, and run live browser sessions, with some account-action and API-key handling risks users should manage deliberately.

Install this only if you intend to let an agent use the Pub CLI with your Pub account. Review deletions, updates, and public/private changes before they run, and handle PUB_API_KEY as a secret using secure config or environment handling where possible. The clean VirusTotal and static scan results support a benign verdict, but they do not remove the need for normal care around account credentials and publishing actions.

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
84% confidence
Finding
The skill documents a destructive `pub delete <slug>` command without any warning, confirmation, or requirement to verify user intent. In an agent setting, this increases the chance of accidental or prompt-induced deletion of user content, especially because the skill also encourages routine reuse and updating of existing pubs.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The API key setup examples encourage passing a sensitive credential directly on the command line or through stdin without any privacy handling guidance. This can expose secrets via shell history, logs, screenshots, or unsafe copy/paste practices, which is especially relevant for agent-operated environments.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal