The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted data from the web.
Ingestion points: External content is fetched and processed through page.content() and page.evaluate() in lib/scraper.ts and lib/crawler.ts.
Boundary markers: The code snippets do not include explicit delimiters or system instructions to ignore embedded commands within the scraped HTML content.
Capability inventory: The skill enables browser automation (Playwright), network requests to arbitrary URLs, and data extraction functionality.
Sanitization: There is no evidence of sanitization or filtering applied to the extracted web content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the playwright package and Chromium browser via npm and npx. These are standard dependencies for browser automation and are sourced from Microsoft, a trusted organization.

crawl-cli