ClawHub
Back to skill

Security audit

LinkedIn

Security checks across malware telemetry and agentic risk

Overview

This LinkedIn skill is coherent and not malicious, but it needs Review because it asks users to handle a sensitive LinkedIn session cookie without enough safety boundaries.

Prefer the browser relay or manual browser login flow. Avoid using the li_at cookie method unless you understand that it can act like a login token; do not paste it into chats or logs, store it only in a proper secret store, and revoke sessions if it may have been exposed. Require explicit confirmation before any LinkedIn message, connection request, acceptance, or other account-changing action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to extract and handle the `li_at` session cookie, which is effectively a bearer credential for the LinkedIn account. Anyone who obtains this cookie may be able to impersonate the user without needing their password or MFA, so presenting this workflow without a prominent security warning or safer handling guidance creates significant account takeover and privacy risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.