The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected. The skill's primary function is to guide an AI agent through a structured SEO audit using standard tools and reference materials.
[PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection because its primary purpose is to ingest and analyze external website content via web_fetch or curl. This risk is inherent to the intended use case of performing SEO audits on third-party websites.
Ingestion points: External website HTML and metadata retrieved via web_fetch or curl as defined in SKILL.md.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided within the skill text for the fetched content.
Capability inventory: The skill uses web_fetch and curl for information retrieval; it does not execute system commands, write to the file system (other than reading specific context files), or perform unauthorized network operations.
Sanitization: The skill does not implement manual sanitization of the fetched HTML, relying instead on the agent's default safety guardrails during content processing.

seo-audit