ClawHub
Back to skill

Security audit

Designing TUIs

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill provides proportionate guidance for creating terminal interfaces, with no hidden execution or sensitive-data access found.

Use this skill for terminal interface projects and specify the target framework. Renderers and exporters are not bundled; review generated code and any separately selected dependencies before running them.

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
  • 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)

Activation includes generic UI requests without requiring terminal-specific context.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

The instruction explicitly triggers on welcome screens, dashboards, wizards, and tool panels, which commonly describe web or desktop interfaces as well as terminal interfaces. Although the surrounding description identifies a TUI skill, this activation rule does not require terminal context or exclude non-terminal UI requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.