ClawHub
Back to skill

Security audit

Linkedin Lead Generation

Security checks across malware telemetry and agentic risk

Overview

This is a coherent LinkedIn lead-research skill, though its generated HTML reports should be treated carefully because profile-derived text is not escaped.

Install only if you are comfortable with an agent browsing LinkedIn and company websites for explicit prospect research. Avoid mass scraping or sensitive profiling, check platform and privacy obligations, and sanitize or review generated HTML/PDF reports before opening or sharing them.

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
91% confidence
Finding
The activation text is broad enough to trigger on common requests like finding clients or leads, which can cause the agent to invoke this skill unexpectedly in contexts the user did not intend. Because the skill performs prospecting and external-site research, overbroad triggering increases the chance of unnecessary browsing, collection of personal/professional data, and generation of sales-oriented outputs without clear user consent.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs creation of an HTML/PDF-style output artifact without notifying the user first, which can lead to unexpected file generation and possible persistence of sensitive prospect data on disk. In a lead-generation context, reports may contain names, profile URLs, company details, and assessments that users may not expect to be stored automatically.

Missing User Warnings

Low
Confidence
95% confidence
Finding
The report builder interpolates untrusted prospect fields such as name, position, location, linkedin_url, needs, and pitch directly into HTML without escaping or URL validation. Because this skill processes external/profile-derived data, an attacker-controlled value could inject HTML or script into the generated report, leading to stored/report-based XSS when the HTML is opened or converted by downstream tooling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.