ClawHub
Back to skill

Security audit

performance-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed performance-review helper that reads code for complexity hotspots and does not show hidden mutation, persistence, or data exfiltration behavior.

Installers should know this skill may activate on broad performance-related phrasing and, if run without a path, it is intended to inspect changed repository files. Use an explicit file or directory when you want tighter scope. Optional gauntlet and kuva integrations may read local code graphs or benchmark outputs, but the inspected skill does not require secrets or make automatic external changes.

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
93% confidence
Finding
The trigger list includes broad natural-language phrases such as 'performance', 'complexity', and 'code feels slow', which can cause the skill to activate in ordinary conversations or loosely related review contexts. Unintended invocation can lead to over-collection of repository context, noisy automated analysis, and execution of workflow steps on files the user did not explicitly intend to scan.

Static analysis

No suspicious patterns detected.