The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using npx playwright test to run suites on the cloud grid and npm install to manage project dependencies.
[EXTERNAL_DOWNLOADS]: The skill downloads the browserstack-local package from the npm registry to enable testing on local or firewalled development environments.
[DATA_EXFILTRATION]: The skill transmits the BROWSERSTACK_USERNAME and BROWSERSTACK_ACCESS_KEY environment variables to the official cdp.browserstack.com WebSocket endpoint for session authentication. This is a standard operation for the well-known BrowserStack testing service.
[DYNAMIC_EXECUTION]: The skill dynamically generates and writes configuration blocks to playwright.config.ts to define connection parameters and browser matrices for cloud execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes external test logs and session metadata retrieved from BrowserStack via MCP tools. This represents a vulnerability surface where malicious content in external logs could attempt to influence the agent's interpretation of test results.
Ingestion points: Test session logs and build metadata fetched through MCP tools such as browserstack_get_logs and browserstack_get_sessions.
Boundary markers: No explicit delimiters or instructions are used to isolate external log content from the agent's reasoning.
Capability inventory: The skill has capabilities for file system modification, package installation, and arbitrary command execution via Playwright.
Sanitization: The skill does not implement specific sanitization or filtering for the retrieved external logs.

browserstack