The Agent Skills Directory

[SAFE]: The skill consists of instructional content and code templates for Playwright. No malicious code, obfuscation, or unauthorized access patterns were detected.
[EXTERNAL_DOWNLOADS]: The CI/CD and Docker configurations provided in ci-cd.md reference official and well-known resources, including Microsoft's container registry (mcr.microsoft.com) and official GitHub Actions from the GitHub organization.
[INDIRECT_PROMPT_INJECTION]: The skill documents web scraping patterns, which constitute an ingestion surface for untrusted data from external websites.
Ingestion points: External web content is accessed via page.goto and extracted using page.$$eval or page.evaluate in scraping.md.
Boundary markers: The provided code snippets do not implement specific boundary markers or instructions to ignore embedded commands in the scraped content, which is typical for boilerplate templates.
Capability inventory: The skill includes patterns for file system writes, specifically for saving session states (testing.md) and screenshots (debugging.md).
Sanitization: No specific sanitization or filtering of scraped text is demonstrated in the extraction logic.

Playwright