Back to skill

Security audit

website-structure

Security checks for vulnerabilities and agentic risk

Overview

This is a website-planning guide with no code execution, persistence, credential access, or hidden data movement.

Before installing, understand that this skill may shape page-planning recommendations and may read project-context files if present. Review those files if they contain private business details, and choose locale paths based on the markets or languages you actually intend to support.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation criteria are very broad and include generic planning phrases like 'which pages do I need' and 'page planning,' which can cause the agent to route ordinary website or marketing requests into this skill even when a more specific skill would be safer or more appropriate. This creates scope confusion and increases the chance of misapplication, especially because the file also instructs reading project-context files and chaining to many other skills, amplifying the effect of an over-broad trigger.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The multi-language mapping gives specific locale examples '/zh-CN, /ja' as recommended structure without indicating that language selection should follow user preference or market requirements. This can implicitly steer outputs toward particular locales without opt-in, which may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.