The Agent Skills Directory

[SAFE]: The skill references numerous official documentation sites and GitHub repositories for established web technologies including Angular, Vue, Next.js, Astro, and Vitest, as well as standards bodies like W3C (WCAG) and OWASP. These references are used for version verification and technical guidance, following standard industry practices for architectural decision-making.
[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read repository-native authoritative sources such as product charters, requirements, and Architecture Decision Records (ADRs) to inform its recommendations.
Ingestion points: Reads docs/product-charter.md, ADRs, and delivery documentation as specified in SKILL.md.
Boundary markers: None explicitly defined for untrusted data ingestion.
Capability inventory: No code execution, file writing, or network transmission capabilities are defined within the skill's scripts.
Sanitization: Not applicable as the skill produces architectural recommendations rather than executable code.
[SAFE]: The skill promotes security best practices in its 'Client-Side Security and Privacy' section, specifically advising against storing secrets in JavaScript-accessible storage, enforcing server-side authorization, and correctly configuring CSRF protections.

frontend-architect