Back to skill

Security audit

Gemini Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a simple workflow-routing skill that tells the agent when to use Gemini CLI or Claude CLI and does not include hidden code, persistence, or destructive behavior.

Before installing, understand that using this skill may route planning, research, web search, or code-review context through Gemini CLI and may hand implementation work to Claude CLI via another skill; only use it when that cross-tool workflow is acceptable for the data in your task.

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