ClawHub
Back to skill

Security audit

Email Marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable email marketing guidance skill with purpose-aligned advice, though users should apply its click-tracking guidance with proper privacy controls.

Before installing, understand that this skill provides marketing advice only. If you use its behavioral segmentation recommendations, make sure your email platform and campaigns honor privacy laws, consent requirements, unsubscribe choices, deletion requests, and reasonable retention limits.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
90% confidence
Finding

The guidance explicitly recommends tagging on every click to build behavioral profiles, but it does not include any privacy notice, consent boundary, retention limit, or jurisdictional caveat. In a marketing skill, this can normalize broad user tracking and profiling practices that may violate privacy expectations or legal requirements if implemented without transparent disclosure and valid consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.