ClawHub

Lensmor Contact Finder

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it uses the Lensmor API to find business contacts for LinkedIn outreach, with privacy and compliance considerations but no hidden behavior found.

Install only if you are comfortable sending company names and role criteria to Lensmor and using returned professional profile data for B2B outreach. Keep LENSMOR_API_KEY secure, verify contacts before messaging, respect LinkedIn/platform terms and do-not-contact preferences, and confirm your organization has an appropriate lawful basis for prospecting in relevant jurisdictions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
76% confidence
Finding
The description contains very broad multilingual trigger phrases such as generic requests to find contacts or decision-makers. In agent environments that use semantic routing, this can cause over-triggering on ordinary user requests and unintentionally route company-identifying queries to this external-data skill, increasing the chance of unintended data disclosure or unexpected external API calls.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to collect company names and role filters, then transmit them to Lensmor's external API, but it does not require any user-facing notice or consent at the moment of sharing. This creates a privacy/transparency risk because user-supplied business targeting information may be sent to a third party without clear disclosure.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The example operationalizes identifying named employees and prioritizing them for unsolicited outreach, but provides no privacy, lawful-basis, or consent guidance. In a contact-finder skill, that omission makes it easier for users to repurpose the workflow for intrusive prospecting, profiling, or non-compliant processing of personal data scraped from LinkedIn or company websites.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal