GTM Outbound Strategy

Security checks across malware telemetry and agentic risk

Overview

This skill only provides instructions for drafting outbound sales messages and does not request code execution, account access, or automatic sending.

Before installing, understand that this skill may appear for some general outreach-writing prompts. Review any generated outreach for accuracy, consent, brand fit, and compliance with email and platform rules before sending.

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
91% confidence
Finding
The trigger phrases are broad natural-language requests like "build an outbound campaign" and "help me write outreach for [company]," which can plausibly appear in normal conversation outside an explicit intent to invoke this skill. This creates an overbroad activation surface where the skill may trigger unintentionally, causing the agent to generate outbound messaging or sales content in contexts the user did not mean to invoke this capability.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal