Back to skill

Security audit

LeadShark Apex

Security checks for vulnerabilities and agentic risk

Overview

The skill openly connects your LeadShark account for LinkedIn automation and directs the agent to keep you involved before posting or messaging.

This connection can access account data and act as you on LinkedIn. Prefer OAuth, review the discovered tools and permissions, and require approval before publishing, messaging or activating automations. Protect any fallback API key. Both scanners reported no findings; the inspected instructions independently support this benign verdict.

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
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