The Agent Skills Directory

[SAFE]: The skill focuses on visual validation and accessibility auditing, which are legitimate development tasks. It uses standard tools like Read, Grep, and Glob to examine local design specifications.
[SAFE]: The skill accesses configuration data via a platform-specific mechanism (/majestic:config). This resource is aligned with the vendor namespace (majesticlabs-dev) and is used to locate design system files for validation purposes.
[SAFE]: While the skill ingests external data from design system files (Step 0), which theoretically presents an indirect prompt injection surface, there are no instructions that would cause the agent to execute untrusted code or exfiltrate data. The ingestion is scoped to reading CSS/design properties.
[SAFE]: No obfuscated content, hardcoded credentials, or remote dependency downloads were identified in the analyzed file.

visual-validator