ClawHub
Back to skill

Security audit

Refactoring Move Features

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain frontend refactoring guide with no hidden execution, credential access, persistence, or unrelated data collection.

Install this as a refactoring aid for frontend work. As with any refactoring skill, review proposed diffs before applying them, especially changes that move public APIs or remove code, but the package itself shows no security-significant hidden behavior.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 10)May include surrounding context.

md
- ID: `fec-refactoring-move-features`
- Category: `review-quality`
- Version: `2.9.0`
- Source: `skills/fec-refactoring-move-features/SKILL.md`

## Description

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
The family reference contains 9 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.

## Common Mistakes
- Choosing a technique by name without checking its preconditions.
- Combining several structural intentions in one diff.
- Assuming a classical class-based form is mandatory in modern frontend code.
- Treating passing tests as proof when the relevant behavior is not covered.

Static analysis

No suspicious patterns detected.