Activecampaign

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ActiveCampaign integration that needs a Maton API key and can change CRM data, but its access is purpose-aligned and it explicitly requires user approval for writes.

Install only if you trust Maton with access to your ActiveCampaign account. Use the narrowest ActiveCampaign permissions available, specify the intended connection when you have multiple accounts, and require clear confirmation before any create, update, delete, webhook, or campaign-affecting operation.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill advertises destructive capabilities such as deleting contacts and updating CRM records but provides no confirmation, authorization, or human-in-the-loop guidance before state-changing operations. In an agent setting, this increases the risk of accidental or over-broad destructive actions against a live ActiveCampaign tenant when a user request is ambiguous or incomplete.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documented proxy request mechanism enables arbitrary authenticated API calls, including write and delete requests, while presenting it as a normal fallback without safety constraints. In this context, the agent could be induced to perform unsupported but dangerous operations directly against the external system, bypassing the narrower semantics and safeguards of predefined actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal