ClawHub
Back to skill

Security audit

analyze frontend structure

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a frontend project structure analyzer, and its directory scanning behavior is disclosed and aligned with that purpose.

Installers should provide an explicit frontend project path and avoid pointing it at unrelated private directories; review generated mapping documents before sharing them because they may reveal internal route, module, and component names.

A.I.G

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

SkillSpector

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
Confidence
92% confidence
Finding
The skill says to invoke it directly whenever a user needs to analyze a frontend project structure, without meaningful scoping, preconditions, or safety boundaries. Overly broad activation guidance can cause the agent to run directory-scanning behavior in contexts where the user request is ambiguous, unnecessary, or points at unintended filesystem locations, increasing the chance of oversharing sensitive project metadata or analyzing the wrong target.

Static analysis

No suspicious patterns detected.