The Agent Skills Directory

[SAFE]: The skill operates entirely within its stated purpose of performing SEO audits. It uses standard MCP tools for browser automation and does not attempt to access sensitive local files or execute unauthorized commands.
[PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks as it processes external web content.
Ingestion points: Website data is fetched via mcp__playwright__browser_navigate and mcp__playwright__browser_evaluate in SKILL.md.
Boundary markers: The skill does not use explicit delimiters for the extracted data, though it targets specific fields like title and meta tags.
Capability inventory: Capabilities are limited to browser-based data extraction and reporting.
Sanitization: The skill utilizes specific attribute selectors and text extraction to minimize the ingestion of executable instructions. Given the skill's primary purpose is web analysis, this surface is considered acceptable and low risk.

seo-check