frontend-design

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided frontend requirements to generate production-grade code, creating an attack surface for indirect instructions. * Ingestion points: The skill accepts arbitrary frontend requirements as input in the SKILL.md trigger context. * Boundary markers: There are no explicit delimiters or instructions provided to isolate user-supplied requirements from the core skill instructions. * Capability inventory: The skill is limited to code generation (HTML, CSS, JS, React, Vue) and lacks tools for network access, file system manipulation, or command execution. * Sanitization: No mechanisms for validating or escaping the input data are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:26 AM
Security Audit — agent-trust-hub — frontend-design