Marketing Automation CLI

• Outcome: Pass
• Latest audit: May 28, 2026, 11:00 AM
• Version:
  1.0.0

Overview

This markdown-only skill provides disclosed marketing workflow templates for official business chat CLIs, but users must enforce consent and approval before sending customer messages or syncing lead data.

Install only if you want an agent to help draft and orchestrate marketing CLI commands against Feishu, DingTalk, and WeCom. Before running any generated command, confirm the target audience, opt-in status, unsubscribe suppression, message frequency limits, approval status, and legal basis for any cross-platform lead or customer-data transfer.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Intent-Code Divergence

High

• Confidence: 98% confidence
• Finding: The workflow copies lead data from WeCom into Feishu Base even though the skill's own safety rules say customer data must not be shared across platforms without consent. This creates a real privacy and compliance risk because names, interests, and contact-related metadata may be transferred and stored in another system without verifying legal basis, customer authorization, or data minimization.

Intent-Code Divergence

High

• Confidence: 99% confidence
• Finding: The nurture sequence sends multiple automated customer messages without first checking opt-in status, unsubscribe state, or message frequency eligibility. That makes the workflow capable of unauthorized outreach and repeated contact to real customers, which can violate anti-spam rules, internal policy, and customer expectations.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: These campaign launch steps send external-facing messages and email but do not present a prominent warning that the actions have live customer communication, privacy, and business impact. In an agent skill, lack of an upfront warning increases the chance that an operator or downstream agent executes broad outbound actions without realizing they affect real recipients.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This lead-tracking workflow processes customer-identifying information across WeCom, Feishu, and DingTalk without an upfront privacy warning. Because it combines search, sync, assignment, and alerting steps, users may underestimate that the workflow handles personal data and triggers cross-system propagation.

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The nurture sequence automates a multi-day outbound messaging campaign to customers without a prominent warning about consent, unsubscribe handling, frequency controls, and live customer impact. In context, this is especially dangerous because the workflow is designed for repeated real-world outreach, so omission of strong guardrails can directly lead to spam or noncompliant customer contact.

VirusTotal

63/63 vendors flagged this skill as clean.