The Agent Skills Directory

[SAFE]: The skill's logic and reference materials are entirely consistent with the stated purpose of providing professional SEO audits and strategic planning.
[COMMAND_EXECUTION]: The skill utilizes standard command-line tools for performance measurement, including npx lighthouse for lab data and curl for interacting with the Google PageSpeed Insights API (references/cwv-thresholds.md).
[PROMPT_INJECTION]: As an SEO tool, this skill possesses an indirect prompt injection surface because it is designed to ingest and process content from external websites.
Ingestion points: Content from any user-provided URL processed via commands like /seo audit, /seo page, or /seo technical (SKILL.md).
Boundary markers: None are explicitly defined in the instructions to separate fetched web data from the agent's internal reasoning instructions.
Capability inventory: The skill can execute subprocesses like npx lighthouse and perform network operations via curl to analyze external resources (references/cwv-thresholds.md).
Sanitization: No specific sanitization or instruction-filtering logic is mentioned for the content retrieved from scanned URLs, as the focus is on metric extraction and qualitative SEO assessment.

seo