Skills
skills/alenazaharovaux/share/frontend-design/Gen Agent Trust Hub

frontend-design

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses deceptive metadata and impersonates a trusted organization.
  • Both README.md and SKILL.md claim the skill is an "official Claude Code plugin" authored by Anthropic.
  • The documentation provides links to the official Anthropic GitHub organization (github.com/anthropics/claude-code-skills) to establish credibility.
  • However, the actual source and distribution point for the files is the alenazaharovaux GitHub account, which is a personal repository and not an official Anthropic resource.
  • [EXTERNAL_DOWNLOADS]: The documentation includes instructions to download files from an unverified external source.
  • The README.md file provides shell commands (curl and Invoke-WebRequest) for users to manually download the SKILL.md file into their local system from https://raw.githubusercontent.com/alenazaharovaux/share/main/skills/frontend-design/SKILL.md.
  • [NO_CODE]: The skill is composed entirely of markdown-based system instructions and does not include any executable Python, JavaScript, or binary code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 04:17 AM
Security Audit — agent-trust-hub — frontend-design