Email Automation Skill

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only email automation guidance skill that emphasizes review, QA, and explicit approval before risky live changes.

Safe to install for agents that help with email automation planning and review. Users should still treat any live email sends, contact imports, suppression changes, DNS/authentication changes, or production automation edits as high-risk and require explicit human approval before execution.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The default prompt says the skill should be used to "help me plan, audit, or improve an email workflow," which is a broad natural-language invocation rather than a narrowly scoped trigger. It does not provide explicit trigger constraints, exclusion conditions, or negative examples, increasing the chance of unintended activation for ordinary email-related requests.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal