claude-wireframe-skill

Warn

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill serves as a stub or pointer that triggers the installation of its full payload from an external GitHub repository (Magdoub/claude-wireframe-skill).
  • [COMMAND_EXECUTION]: The skill provides several shell commands for environment detection and installation, and explicitly encourages executing these commands using the '!' prefix to run them directly within the agent's environment.
  • [REMOTE_CODE_EXECUTION]: The installation procedure uses npx to fetch and execute code from a remote source, which effectively performs remote code execution to set up the full skill.
  • [DATA_EXFILTRATION]: The skill is designed to scan the user's entire codebase upon its first execution to build a persistent design context, which represents a significant data access surface for all project files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — claude-wireframe-skill