ClawHub
Back to skill

Security audit

Vibe Coding Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only coaching skill for AI-assisted app building, with no code execution, persistence, credential use, or hidden data handling.

Installers should understand this skill may be invoked for broad AI app-building questions. Its guidance is educational, but users should still review any AI-generated code, keep secrets out of prompts, and get professional review for authentication, payments, privacy, or production systems.

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
90% confidence
Finding
The trigger list includes broad phrases such as "I want to build an app using AI," "build this without coding," and "help me prompt for this feature," which could match many ordinary requests outside a narrowly defined skill invocation context. The file provides example triggers but does not include exclusion conditions or boundaries to reduce unintended activation.

Static analysis

No suspicious patterns detected.