ClawHub
Back to skill

Security audit

Swift

Security checks across malware telemetry and agentic risk

Overview

This is a Swift coding-assistance skill whose local preference memory is disclosed and purpose-aligned, though users should know it can reuse and store Swift-related preferences under their home directory.

Before installing, be aware that the skill may maintain Swift-specific config and memory files under ~/Clawic/data/swift/. Review or delete those files if you do not want prior project context, coding preferences, or corrections reused in future Swift assistance.

SkillSpector

By NVIDIA
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 instructs the agent to read persistent local preference and memory files containing prior user context without any requirement to disclose that access to the user or obtain consent. This creates a privacy and context-leak risk because stored personal or project information may be silently incorporated into responses, especially since the skill explicitly says 'Do not interview the user,' reducing transparency.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill directs the agent to persist user preferences, habits, and corrections to local files without telling the user that this data will be stored. Silent persistence of behavioral preferences and recurring pain points can accumulate sensitive profile data over time and may exceed user expectations for a coding assistant interaction.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.