The Agent Skills Directory

[SAFE]: The skill performs legitimate SEO analysis tasks using a defined set of tools for Google Search Console data retrieval and on-page auditing. The workflow is transparent and consistent with the stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes external content from web pages during the audit_onpage_seo step. This represents a standard data ingestion surface for SEO tools. The risk is low as the output is restricted to SEO rewrite briefs and does not involve executing commands or accessing sensitive local files.
Ingestion points: External web page titles and metadata are ingested via the audit_onpage_seo tool (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided for the ingested data.
Capability inventory: The skill's capabilities are limited to data analysis and text generation (rewrite briefs).
Sanitization: No specific sanitization or filtering of the ingested metadata is mentioned.

ctr-optimization