Security audit

Lemlist

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Lemlist outreach, but it asks users to install and allow an unpinned external plugin that handles OAuth-backed Lemlist access and can perform business-impacting writes.

Review the ClawLink plugin source, publisher, version, and update policy before installing. Connect only a Lemlist account with the minimum needed permissions, verify previews before any write operation, and be especially careful with campaigns, lead status changes, schedules, unsubscribe/suppression changes, and exports.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:46
Finding: Unpinned Third-Party Plugin Is Installed and Granted Tool Access
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The table entry describes lemlist_get_contact_messages as "Get all messages exchanged with a specific contact," which is a read-only retrieval operation by its own wording, but the Mode column marks it as Write. This is an active documentation contradiction that could mislead an agent's confirmation and safety workflow.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.