The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell and Node.js scripts (run-assessment.sh, generate-html-report.js) to perform browser automation and data processing.
[COMMAND_EXECUTION]: The report generation script starts an ephemeral local HTTP server to host the results and utilizes child_process.exec to automatically launch the default system browser.
[EXTERNAL_DOWNLOADS]: The skill uses npx to run Playwright and optionally integrates with Vibium, which involves fetching well-known packages from the npm registry.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it analyzes content from arbitrary target URLs provided by the user.
Ingestion points: The testability-scoring.spec.template.js file navigates to and extracts data from external websites.
Boundary markers: The analysis logic does not implement explicit delimiters or instructions to ignore potential injection patterns within the processed web content.
Capability inventory: The skill can execute shell commands, perform local file writes, and open local network ports.
Sanitization: No evidence of sanitization was found for the external page content before it is incorporated into assessment metrics.

testability-scoring