ClawHub
Back to skill

Security audit

Search Google for LinkedIn and locate the official sign-in result

Security checks across malware telemetry and agentic risk

Overview

This skill only searches Google for LinkedIn and identifies a visible official linkedin.com result without signing in, reading credentials, or saving anything.

Before relying on the result, visually confirm the destination is linkedin.com or an expected LinkedIn subdomain, avoid sponsored or ambiguous results, and stop if the official domain is not clearly shown.

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
95% confidence
Finding
The workflow is triggered by a very broad, everyday query ('linkedin') and does not clearly constrain when it should be used or what trust checks are required beyond visually finding a result. In an automated or semi-automated browsing context, this can normalize search-engine-mediated navigation to sensitive login pages and increase exposure to phishing, ads, spoofed results, or unintended execution in unrelated contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.