The Agent Skills Directory

[SAFE]: The skill provides comprehensive guidelines for setting up and running E2E tests for RedisInsight. It promotes best practices such as test isolation, stateless page objects, and clean teardown procedures.
[COMMAND_EXECUTION]: Instructions include standard shell commands for running tests via the Playwright CLI (e.g., npx playwright test). These are legitimate development tools necessary for the skill's stated purpose.
[EXTERNAL_DOWNLOADS]: The skill references standard, reputable development libraries for testing, including fishery and @faker-js/faker for data generation. These are widely used and well-known in the Node.js ecosystem.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it directs the agent to interact with and process UI content from a live browser using Playwright MCP. While malicious content on a target web page could theoretically attempt to influence the agent's behavior, this is an inherent and expected risk of UI automation tasks, not a defect of the skill itself.
Ingestion points: UI snapshots and element trees processed via browser_snapshot_Playwright and browser_navigate_Playwright.
Boundary markers: None explicitly defined for untrusted UI content.
Capability inventory: Navigation, element interaction (click, type), and shell execution for running test suites.
Sanitization: Not applicable to the processing of UI element metadata in this context.

e2e-testing