Back to skill

Security audit

Lead Nurture

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed lead-nurture content generator with CRM export guidance, but users should add compliance checks before using its email or SMS automation outputs.

Before installing or using this skill operationally, treat all generated email and SMS sequences as draft marketing material. Review them for applicable CAN-SPAM, TCPA, GDPR, platform rules, opt-out handling, sender identification, quiet hours, consent records, and suppression lists before importing or activating them in any CRM or marketing automation system.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is explicitly designed to generate and export automated email/SMS nurture sequences, including resend logic, branching, and CRM-ready automation, but it provides no compliance, consent, opt-out, or human-review safeguards. In this context, the omission is dangerous because it facilitates immediate operational use of potentially unlawful or abusive outreach at scale across regulated channels like SMS and email.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The integration notes directly instruct users how to import generated content into live CRM/marketing automation systems such as GoHighLevel, Follow Up Boss, and Mailchimp, but omit any warning that these workflows may send real messages automatically. That makes the skill more dangerous in context because it lowers the barrier from content generation to mass deployment without checks for consent, audience segmentation, rate limits, or human approval.

Content

No source excerpt is available for this finding.