Mailjet

Security checks across malware telemetry and agentic risk

Overview

This Mailjet skill is a legitimate integration, but it gives an agent broad authenticated power to send email and change or delete Mailjet data without clear confirmation safeguards.

Install only if you are comfortable granting Membrane-managed access to the intended Mailjet account. Before sending emails, deleting lists, changing contacts, or using the raw proxy, require the agent to show the exact action, target ID or name, HTTP method, endpoint, and payload, then get explicit confirmation.

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: 93% confidence
Finding: The skill advertises destructive capabilities such as deleting contact lists without any confirmation, authorization, or 'are you sure' guidance. In an agentic setting, this increases the risk that a vague, mistaken, or prompt-injected instruction could trigger irreversible state changes in a user's Mailjet account.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal