ClawHub
Back to skill

Security audit

Swiftdata Patterns

Security checks for vulnerabilities and agentic risk

Overview

This is a SwiftData guidance skill with ordinary code examples and no hidden execution behavior.

Before copying the examples into a real app, confirm that cascade deletes, App Group storage, and CloudKit syncing match your intended data-retention and privacy behavior.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file includes a pattern using deleteRule: .cascade and labels it as auto-deleting children, but it does not warn that deleting a parent will irreversibly remove related child data. For markdown files, destructive behaviors affecting user data should be accompanied by an explicit warning about data-loss implications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.