Back to skill

Security audit

code-review-skill-agent

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only backend code review guide with no executable code, persistence, credential handling, or hidden data movement.

Before installing, users should understand that this skill enforces a strict backend review policy tied to AGENTS.md and repository skill files. That may be appropriate for teams using that workflow, but it could produce irrelevant review rejections in repositories that do not follow those conventions.

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