Back to skill

Security audit

Nextjs

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Next.js guidance skill with broad wording but no executable code, persistence, credential handling, or hidden behavior.

Use this as lightweight Next.js development guidance. Because it mentions auth, caching, and production patterns, review generated changes before applying them to real applications, especially where security, secrets, deployment, or user data are involved.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill's invocation guidance is so broad that an agent may apply it to a wide range of loosely related developer tasks without clear boundaries or preconditions. This increases the risk of inappropriate tool use, overreach into security-sensitive coding tasks, or generation of production-impacting Next.js/auth/caching code in contexts where more specialized review or constraints are required.

Content

No source excerpt is available for this finding.