frontend

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs common frontend libraries including Tailwind CSS, Framer Motion, and Lucide React from the official NPM registry during the setup phase.
  • [COMMAND_EXECUTION]: Utilizes shell commands (Bash) to manage project dependencies and initialize UI component frameworks using standard tools like npm and npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied UI requirements which are interpreted to generate code. This creates a surface for potential instruction injection through the project description.
  • Ingestion points: User input following the /frontend command in SKILL.md.
  • Boundary markers: None explicitly defined to separate user requirements from agent instructions.
  • Capability inventory: File system access (Write, Edit) and shell execution (Bash) allowed in the frontmatter.
  • Sanitization: No specific sanitization or filtering of the user-provided requirements is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:41 PM
Security Audit — agent-trust-hub — frontend