ClawHub
Back to skill

Security audit

Dev Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SwiftUI project generator with disclosed file output and QA handoff behavior, and no evidence of hidden execution, persistence, credential access, or exfiltration.

Before installing, expect this skill to write a multi-file Xcode project into dev-output/ and then pass the generated code to qa-skill. Use it in a workspace where that output path is acceptable, and check for existing files before generation.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly states it will create a complete Xcode project in `dev-output/`, but the user-facing description does not clearly warn that it will write a multi-file project to disk automatically. That can lead to unexpected filesystem modifications, overwriting existing contents, or user surprise in environments where file creation should be explicitly authorized.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The description mentions that the skill automatically triggers `qa-skill` after code generation, but it does not present this as a clear user warning or consent-requiring downstream action. Automatic chaining can expose generated artifacts to additional processing the user did not explicitly request, reducing transparency and control over agent behavior.

Static analysis

No suspicious patterns detected.