ClawHub
Back to skill

Security audit

LinkedIn Profile Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown LinkedIn profile rewriting skill whose requested profile text is purpose-aligned, though users should redact sensitive details before pasting.

Before installing or using this skill, redact contact details, private URLs, confidential employer or client information, and any third-party personal data from the LinkedIn text you paste. The skill itself is a prompt-only profile optimizer and does not install code or request account access.

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 instructs users to paste full LinkedIn profile sections, including experience entries and optional featured content, without any warning to avoid sharing sensitive personal, confidential, or third-party information. This creates a realistic privacy risk because users may disclose employer-confidential details, client names, personal identifiers, or other data that is unnecessary for optimization and could be retained or exposed downstream.

Static analysis

No suspicious patterns detected.