The Agent Skills Directory

[SAFE]: The skill serves as a high-quality educational resource for frontend testing. It correctly identifies and promotes security best practices, such as pinning external GitHub Actions to specific commit SHAs and using least-privilege permissions in CI/CD workflows.
[EXTERNAL_DOWNLOADS]: The documentation references industry-standard tools and libraries, including @axe-core/playwright for accessibility testing and official GitHub Actions (actions/checkout, actions/upload-artifact). These are well-known services and do not represent a security risk.
[COMMAND_EXECUTION]: The skill provides standard example commands for test execution and baseline management (e.g., npx playwright test). These commands are typical for the developer workflows described and are legitimate within this context.
[PROMPT_INJECTION]: The skill defines a workflow for ingesting external requirements data like ticket descriptions and Figma annotations to generate tests. While this creates a surface for indirect prompt injection, it is standard for development tasks.
Ingestion points: Ticket descriptions, Figma annotations, and stakeholder clarifications (SKILL.md).
Boundary markers: None specified to delimit external content.
Capability inventory: Code generation and execution through Vitest and Playwright.
Sanitization: No specific sanitization or validation of the ingested criteria is mentioned.

frontend-testing