The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands via the Bash tool to build and test the application, including dotnet test, dotnet run, and executing the ./run-e2e-tests.ps1 script.\n- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to interact with and read from web page content, which creates a vulnerability surface for indirect prompt injection if the agent is instructed to process or act upon the content being tested.\n
Ingestion points: Browser content is retrieved through Page.Locator, TextContentAsync, and Page.GetByTestId as seen in references/patterns.md and references/workflows.md.\n
Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from following instructions found within the application's UI.\n
Capability inventory: The agent has the ability to execute local commands via the Bash tool and make network requests using HttpClient.\n
Sanitization: No mechanisms for sanitizing or filtering data extracted from the browser are implemented in the provided patterns.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions for installing Playwright and its dependencies, which involves downloading browser binaries from official sources during local setup and CI/CD runs.\n- [DYNAMIC_EXECUTION]: The skill uses WaitForFunctionAsync to execute JavaScript snippets within the browser's context to validate application state. This is a standard feature of the Playwright library for handling complex wait conditions in E2E tests.

playwright