Security audit

Constant Contact

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Constant Contact admin/API skill with high-impact write abilities, but its behavior is coherent with its stated purpose and requires user confirmation for writes.

Install this only if you want an agent to administer your Constant Contact account through Maton. Review every proposed write, bulk change, connection deletion, sender email change, and campaign send/schedule action before approving it, because those actions can affect subscribers or send external emails.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The manifest understates the skill's effective scope by claiming focus on marketing data while the document also exposes account-management and OAuth connection-management capabilities. This can mislead users or downstream policy systems about the true authority of the skill, increasing the chance of approving broader actions than intended.

Context-Inappropriate Capability

Low

Confidence: 83% confidence
Finding: Including generic connection lifecycle operations broadens the skill beyond its stated purpose of interacting with Constant Contact marketing data. That extra capability can let an agent create, inspect, or delete integrations and switch account context, which expands administrative risk and can facilitate misuse if invoked improperly.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.