The Agent Skills Directory

[SAFE]: The skill's functionality is transparent and matches its described purpose of performing technical SEO audits. It utilizes standard MCP (Model Context Protocol) tools to fetch and analyze page metadata, headings, and structured data.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection as it is designed to ingest and process data from external URLs.
Ingestion points: The url parameter in seo_run_report (referenced in SKILL.md) triggers the fetching of untrusted external content.
Boundary markers: The instructions distinguish between the structuredContent machine contract and the Markdown human explanation, providing a logical boundary for the agent.
Capability inventory: The skill uses seo_run_report to fetch data and relies on the agent to interpret findings; it does not contain dangerous command execution or file-write capabilities.
Sanitization: No explicit sanitization or filtering of fetched content is documented in the skill instructions.

audit-page