Back to skill

Security audit

Engagement Suppression Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed HubSpot workflow guide for re-engaging inactive contacts before suppressing them, with business-impact risk that users should test carefully.

Before installing or using this skill, confirm the enrollment filters on a small segment, review the non-marketing action with the team responsible for email reach, and keep a way to identify and reverse affected contacts if the criteria are too broad.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill directs users to set contacts to non-marketing/suppressed status, which can materially change user outreach and business operations, but the main workflow guidance does not prominently warn about the consequences of suppressing legitimate contacts or the need for stakeholder approval before activation. In this context the behavior is intentional and aligned with the workflow’s purpose, so it is not malicious, but it is still a real safety issue because misconfiguration or overbroad triggers can silently remove contacts from marketing eligibility at scale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.