The Agent Skills Directory

[SAFE]: The skill uses Playwright MCP tools for their intended purpose of navigating to and evaluating web pages. No evidence of malicious activity such as data exfiltration, credential harvesting, or persistent access was found.
[PROMPT_INJECTION]: The skill navigates to external URLs, which represents a surface for indirect prompt injection. However, it is configured to extract only numeric performance metrics, minimizing risk.
Ingestion points: mcp__playwright__browser_navigate uses user-supplied URLs in SKILL.md.
Boundary markers: None.
Capability inventory: mcp__playwright__browser_navigate, mcp__playwright__browser_evaluate, and mcp__playwright__browser_click are used in SKILL.md.
Sanitization: None.

core-web-vitals