a11y-playwright-testing
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references standard development dependencies used for testing web applications.
- The instructions recommend installing
@playwright/test,@axe-core/playwright, andaxe-corevia NPM. - These are well-known, industry-standard packages from the official NPM registry, maintained by Microsoft and Deque Systems.
- [INDIRECT_PROMPT_INJECTION]: The skill implements patterns for ingesting and analyzing data from external, potentially untrusted web applications during the testing process.
- Ingestion points: The
page.goto()calls and role-based locators described inSKILL.md,references/snippets-setup-and-scanning.md, andreferences/snippets-keyboard-focus-semantic.mdingest text content, attributes (likearia-label), and structural data from the DOM of the application under test. - Boundary markers: The provided test snippets do not include specific delimiters or instructions to prevent the agent from interpreting extracted DOM content as instructions rather than data.
- Capability inventory: The skill utilizes Playwright capabilities including full browser control, keyboard emulation, mouse events, and execution of arbitrary JavaScript within the browser context via
page.evaluate(). - Sanitization: There is no evidence of content sanitization or validation performed on the text extracted from the web pages before it is processed for test assertions or inclusion in test reports.
Audit Metadata