Emaillistverify

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate EmailListVerify integration, but it gives an agent broad authenticated access including deletion and raw API requests without clear confirmation safeguards.

Install only if you trust Membrane with delegated access to the intended EmailListVerify account. Before using it, require the agent to show the exact action, connection, target list or job, and parameters before any delete, bulk, or raw proxy request.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 73% confidence
Finding: The invocation text is broad enough that an orchestrator could select this skill for generic requests about EmailListVerify data, even when the user's intent is ambiguous. In a network-enabled skill that can query account state and perform actions, overbroad routing increases the chance of unintended external access or actions on the wrong system.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill advertises a destructive 'Delete Email List' capability without documenting any requirement for confirmation or safety checks. In an agentic setting, that omission raises the risk that a model could delete verification jobs or data as part of a loosely phrased request or mistaken action selection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal