ClawHub
Back to skill

Security audit

Analyzes code for improvements including code smells, design patterns, and best practices. Invoke when user asks for code analysis, code review, or suggestions to improve code quality.

Security checks for vulnerabilities and agentic risk

Overview

This is a simple code-quality review skill with broad routing language but no hidden execution, persistence, credential access, or destructive behavior.

Before installing, understand that this skill may be selected for general code review requests and will steer the agent toward maintainability, readability, refactoring, and performance feedback. It does not appear to add code execution or privileged access, but it should not be relied on as a dedicated security or debugging review skill unless separately instructed.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description uses broad triggers like 'code analysis' and 'code review' without constraints, which can cause the orchestrator to invoke this skill for a wide range of ordinary developer requests. Over-broad routing increases the chance of inappropriate skill activation, potentially displacing a more suitable skill or causing the agent to follow this skill's output format when the user did not ask for it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The 'When to Use' section lists ambiguous activation conditions such as 'user asks for code analysis or code review' and mentions generic terms like 'best practices' without boundaries. In an agent setting, this can lead to overly aggressive invocation on common requests, creating prompt-routing confusion and increasing the risk that relevant concerns such as security, debugging, or functional correctness are handled by a code-quality-oriented skill instead.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.