ClawHub
Back to skill

Security audit

Vibe Coding

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only educational skill about using AI coding tools, with one loose autonomy tip but no hidden execution, data access, or persistence behavior.

Installers should treat this as general advice, not a license to delegate sensitive work blindly. Use the workflow sections that call for reviewing plans, checking diffs, testing changes, and manually scrutinizing auth, payments, permissions, schemas, secrets, and user data handling.

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 (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The guidance 'Let it run — it's designed for autonomy' encourages users to allow an AI coding agent to execute multi-step actions without emphasizing review, permission boundaries, or verification of changes. In a software-development skill, this can normalize unsafe delegation to tools that may modify code, secrets, dependencies, or infrastructure in ways the user does not inspect before impact occurs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.