ClawHub
Back to skill

Security audit

LinkedIn Authority — Thought Leadership System

Security checks for vulnerabilities and agentic risk

Overview

The skill is a LinkedIn content and outreach guide with no executable code, but users should apply privacy, anti-spam, and LinkedIn policy judgment when using its prospecting templates.

Installers should treat this as a marketing-writing aid, not an authorization to scrape prospects or send unsolicited bulk messages. Use the templates only with relevant contacts, respect LinkedIn rules and applicable anti-spam/privacy laws, and avoid using personal profile-view or engagement data for follow-up unless permitted and appropriate.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill provides outreach, follow-up, and profile-viewer tracking tactics without any guidance on consent, privacy expectations, platform rules, or lawful processing of personal data. In a marketing/prospecting context, this can normalize intrusive contact practices or unauthorized use of personal information, increasing the risk of spam complaints, policy violations, or privacy noncompliance.

Static analysis

No suspicious patterns detected.