ClawHub
Back to skill

Security audit

Shadcn Ui

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-style helper for building shadcn/ui components and does not show hidden, destructive, or unrelated behavior.

Installers should treat this as a normal UI-development helper. Before running documented shadcn CLI commands, confirm the target project directory and review version-control diffs, especially when using --overwrite or adding many components.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Content
### Common Options

- `-y, --yes` - Skip confirmation prompt
- `-o, --overwrite` - Overwrite existing files
- `-c, --cwd <cwd>` - Set working directory
- `--src-dir` - Use src directory structure
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Static analysis

No suspicious patterns detected.