Back to skill

Security audit

Email Automation Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped email-automation planning and review guide that explicitly separates recommendations from live-system changes.

Installers should treat this as an advisory workflow skill for email automation reviews. Before allowing any real provider changes, confirm the human owner, approval process, rollback plan, consent and suppression state, and whether the action affects live sends or production journeys.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt says to use the skill to 'help me plan, audit, or improve an email workflow,' which describes broad, everyday assistance tasks without clear activation boundaries or exclusion conditions. In a manifest file, this can create ambiguity about when the skill should invoke versus when a general assistant should simply answer a normal email-related question.

Content

No source excerpt is available for this finding.