Security audit

Email Marketing Command Center

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing guidance skill, not executable code, and its privacy-sensitive segmentation advice is visible and generally purpose-aligned.

Install only if you want your agent to help with email marketing. Use anonymized metrics where possible, do not paste full subscriber lists or personal data unless necessary, and confirm consent, unsubscribe, retargeting, SMS, GDPR/CASL/CCPA, and ad-platform requirements before acting on the segmentation or cross-channel advice.

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

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 (4)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The quick-command phrases are broad, natural-language triggers like 'write a newsletter' and 'optimize this email' that can easily match ordinary user requests outside a deliberate skill invocation flow. This can cause unintended activation of the skill, leading the agent to apply marketing-specific behaviors or expose workflow guidance when the user did not explicitly intend to use this skill.

Missing User Warnings

Medium

Confidence: 81% confidence
Finding: The skill promotes behavioral segmentation, tagging based on clicks and page visits, and inferred interests without an upfront privacy notice or consent guardrail. In practice, this could encourage collection and processing of engagement data in ways that violate user expectations or privacy obligations, especially in regulated jurisdictions.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The cross-channel section explicitly recommends moving non-openers and clickers into Facebook/Google retargeting audiences and coordinating email engagement with ads and SMS, but it does not warn about consent, data sharing, or platform-policy constraints. This creates a real risk of repurposing subscriber engagement data across channels without adequate disclosure or legal basis.

Missing User Warnings

Low

Confidence: 82% confidence
Finding: The quick-start examples encourage users to provide campaign metrics and subscriber-list context such as re-engaging 5,000 cold subscribers. In a markdown skill description, this kind of data-affecting or privacy-relevant behavior should include a brief warning to avoid sharing personal subscriber data or sensitive account information unnecessarily.

Static analysis

No suspicious patterns detected.