ClawHub
Back to skill

Security audit

Swift Patterns

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only SwiftUI guidance skill with no hidden execution, persistence, or credential handling found.

Install this when you want SwiftUI review and refactoring guidance. As with any coding skill, review proposed edits before applying them to important app flows, but no hidden or excessive authority was found in the artifact.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Content
This skill focuses on **facts and best practices** from Apple's documentation:
- Modern APIs over deprecated ones
- Clear state ownership patterns
- Performance-conscious view composition
- Testable code structure
- No architectural mandates (MVVM/VIPER not required)
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Navigation path state appears in multiple places or is being redefined
- List identity changes could reset selection or row state
- Async work was moved or detached from view lifecycle
- Refactor scope touches multiple screens or core flows without verification
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.