lemlist

• Outcome: Pass
• Latest audit: Jun 16, 2026 at 10:13 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed lemlist read-only connector helper, with no artifact evidence of hidden exfiltration, destructive behavior, or automatic state changes.

Before installing, understand that this skill can read lemlist campaign, lead, and team data through your connected OOMOL account. Use it only in workspaces where that business/contact data is appropriate to expose to the agent, and review any oo CLI setup or connection prompts before completing them.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: The manifest and skill metadata present this skill as limited to searching and reading lemlist data, but the body explicitly instructs the agent to inspect and run arbitrary connector actions and discusses write/destructive operations. This creates a capability mismatch that can mislead users, policy layers, or orchestration logic into treating the skill as read-only when it may actually perform state-changing actions.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger text says to use this skill for ANY lemlist request and instead of calling the API directly, which is overly broad and can cause the skill to be invoked in contexts beyond its narrow documented purpose. Overbroad routing increases the chance of unintended tool use, including executing actions with wider privileges than necessary.

VirusTotal

63/63 vendors flagged this skill as clean.