The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Downloads standard, well-known testing libraries (@playwright/test, @axe-core/playwright) and browser binaries (Chromium) from the official NPM registry and Playwright infrastructure. These resources are well-known services and do not escalate the verdict.
[COMMAND_EXECUTION]: Uses npm and npx to install dependencies and run the Playwright test engine. These commands are localized to the project environment and align with the skill's stated purpose.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting untrusted project data (e.g., package.json, design-brief.md, and scene files) to guide test generation.
Ingestion points: reads package.json, vite.config.js, design-brief.md, and all files in src/ (SKILL.md).
Boundary markers: None present to distinguish project data from agent instructions.
Capability inventory: Performs npm install, file system writes to tests/, and npx playwright test (SKILL.md).
Sanitization: No explicit sanitization of ingested file content before processing.

qa-game