ManyChat

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ManyChat integration that can manage subscriber data and send messages, so it should be used only with deliberate approval for account changes or outreach.

Install only if you trust Maton as the authentication proxy for your ManyChat account. Keep MATON_API_KEY and connection URLs private. Before approving any write or message send, verify the connection/account, recipient or subscriber IDs, message text, fields/tags being changed, and that you have proper consent for outreach.

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 (1)

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill documents operations that can send messages, create/update subscribers, and modify tags and fields, but the surrounding guidance does not consistently foreground privacy, consent, and data handling risks near the operational examples. Although a later section mentions explicit approval for write operations, the quick-start and API reference sections make impactful actions easy to invoke without repeated user-facing warnings, increasing the chance of accidental misuse.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal