Back to skill

Security audit

Review Structure

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable code-review skill that asks the agent to inspect repository changes for maintainability issues, with no evidence of hidden execution, credential access, persistence, or exfiltration.

Install this if you want a strict structural code-review assistant. It may read and quote repository files while reviewing, but the inspected artifact does not request automatic code changes, credential access, network transfer, persistence, or privileged actions.

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.