ClawHub
Back to skill

Security audit

RedHat Code Refactor Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a simple refactoring guidance skill with no hidden execution, persistence, network behavior, or credential handling, though its trigger metadata should be cleaned up.

Before installing, fix or verify the trigger configuration so the skill only activates for intentional refactoring requests. Use it on repositories where code edits and test commands are acceptable, and provide a clear target area plus validation commands.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger configuration is effectively unspecified and uses an ambiguous placeholder-like value, which can cause the skill to activate unpredictably or outside its intended context. For a code-refactoring skill, unclear activation scope increases the risk of accidental invocation on sensitive repositories or unintended workflow execution, which may lead to unauthorized code modifications or misuse in broader agent contexts.

Content

No source excerpt is available for this finding.