ClawHub
Back to skill

Security audit

enrich-linkedin-profile

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed LinkedIn profile enrichment workflow that uses Cargo and aiArk to return profile details and a verified work email, with cost controls called out.

Install only if you are comfortable sending LinkedIn profile URLs to Cargo/aiArk for enrichment and using Cargo credits. Confirm the active Cargo account/workspace first, require a valid LinkedIn URL before running, and approve any batch size and estimated credit cost before processing a list.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger list includes broad phrases such as "who is this person" and "enrich LinkedIn data," which can overlap with ordinary user requests and cause the skill to activate when the user did not explicitly intend LinkedIn enrichment or external data collection. In this skill’s context, unintended activation is more concerning because it can lead to third-party API calls, account/session creation, and potential credit consumption on user data without clear consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.