ClawHub
Back to skill

Security audit

swift-expert

Security checks across malware telemetry and agentic risk

Overview

This is a Swift coding-assistant skill made only of instructions, with no scripts, install hooks, credential use, or hidden runtime behavior.

Install only if you want a Swift-focused coding assistant. Review generated diffs and run your own tests, linting, profiling, and accessibility checks before trusting claims about quality, performance, or coverage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill's invocation guidance is broad and lacks concrete activation boundaries, so an orchestrator may invoke it for loosely related requests or let it take on work beyond Swift-specific tasks. In a multi-skill agent system, this can cause inappropriate delegation, excessive access to project context, or unintended modification recommendations outside the user's actual intent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal