Back to skill

Security audit

Create Plan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only planning helper with no executable code, persistence, credential handling, or hidden high-impact behavior.

This skill is appropriate if you want an agent to draft a plan before making changes. It may read relevant project files to ground the plan, but its own instructions tell it not to edit files unless you separately authorize implementation.

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

Static analysis

No suspicious patterns detected.