The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documents the use of external resources for performance auditing.
References npx lighthouse, which downloads and runs the lighthouse package from the npm registry.
Includes an API endpoint https://www.googleapis.com/pagespeedonline/v5/runPagespeed for fetching performance data from Google's services.
[COMMAND_EXECUTION]: The skill provides command-line instructions for performing technical SEO analysis.
Contains shell command examples using curl and npx within the documentation to interact with external APIs and auditing tools.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves fetching and processing data from external, user-supplied URLs.
Ingestion points: Untrusted data enters the agent context through the <url> argument in commands such as /seo audit, /seo page, and /seo technical (defined in SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions embedded within the content of the analyzed URLs.
Capability inventory: The skill documentation references the ability to execute network requests via curl and run Node.js packages via npx (defined in references/cwv-thresholds.md).
Sanitization: There is no evidence of validation or sanitization of the content retrieved from external URLs before it is processed by the agent.

seo