ClawHub
Back to skill

Security audit

Component Library Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill performs read-only component-library audits using local search commands and does not show hidden, persistent, destructive, or data-exfiltrating behavior.

Before installing, confirm you want broad local searches over the repository where the skill is invoked. It is best used in a front-end component library or design-system repo; its grep-based results may need human verification.

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
86% confidence
Finding
The 'Use when' line lists phrases such as 'check component quality' and 'are our components consistent', which are relatively broad natural-language requests and may overlap with ordinary engineering discussion. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Static analysis

No suspicious patterns detected.