Lemlist

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate Lemlist integration, but it gives an agent broad authenticated ability to change or delete outreach data without clear confirmation safeguards.

Install only if you trust Membrane and need Lemlist automation. Use a least-privileged Lemlist account where possible, prefer predefined Membrane actions over raw proxy calls, and require the agent to summarize and get confirmation before any write, delete, bulk update, or outreach-sending action.

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: 92% confidence
Finding: The skill explicitly documents raw proxy access with state-changing HTTP methods like POST, PUT, PATCH, and DELETE, but does not instruct the agent to obtain explicit user confirmation before mutating or deleting data. In an agent setting, this can enable unintended or overly broad changes to production Lemlist data if the model interprets ambiguous requests too aggressively.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal