ClawHub
Back to skill

Security audit

Linkedin Employee Advocacy

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guidance skill for running a LinkedIn employee advocacy program, with no evidence of hidden code, data access, persistence, or automatic posting.

Before installing, treat this as a business-process playbook: make sure any employee posting program has clear consent, brand/legal review rules, and compliance handling for regulated claims or confidential information. The trigger wording could activate for a general team-posting request, but the skill itself is coherent and non-executing.

SkillSpector

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
91% confidence
Finding
The manifest description says the skill triggers on phrases including "get the team posting," which is a common-language request that could arise outside the specific context of a LinkedIn employee advocacy program. Although some listed triggers are domain-specific, this phrase is broad enough to create ambiguity about when the skill should activate.

Static analysis

No suspicious patterns detected.