The Agent Skills Directory

[SAFE]: The skill strictly adheres to its documented purpose of SEO analysis. All instructions and references are consistent with current search engine optimization best practices and guidelines from 2025-2026.
[PROMPT_INJECTION]: The skill contains a vulnerability surface for Indirect Prompt Injection (Category 8) because it retrieves and processes content from external URLs provided by users. However, this is an inherent necessity for its functionality and no malicious exploitation instructions were present.
Ingestion points: Website content retrieved from user-supplied URLs via commands like /seo audit <url> (SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" warnings for external content were identified in the markdown files.
Capability inventory: References to execution of curl for API data and npx lighthouse for performance auditing (references/cwv-thresholds.md).
Sanitization: No explicit sanitization or filtering logic is defined for the ingested website content within the provided files.
[EXTERNAL_DOWNLOADS]: The skill references standard tools and APIs, such as the PageSpeed Insights API and the Lighthouse CLI. These are well-known industry tools used for diagnostic purposes.
Evidence: curl "https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url=URL&key=API_KEY" and npx lighthouse URL (references/cwv-thresholds.md).

seo